© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2852
    Prev
    Next
    INDEX
    Explanations

    a jumble of words related to medicine, Russian language characters, networking protocols, and the word 'response'

    oai_token-act-pair · gemini-2.0-flash

    words related to combat and medical terminology

    np_token-act-pair-logits · gpt-4o-mini

    medical/scientific texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.83
    ftagPool
    -0.80
    ंदीखरीदारी
    -0.70
    yntaxException
    -0.68
    hyrchwyd
    -0.63
    wpi
    -0.62
     defaultstate
    -0.61
    MigrationBuilder
    -0.60
     Anker
    -0.58
    fjspx
    -0.58
    POSITIVE LOGITS
     tuong
    0.48
     getText
    0.46
     recours
    0.46
     délib
    0.45
     étoient
    0.45
     raccol
    0.45
     solidarité
    0.44
     ladite
    0.43
    ядок
    0.43
     informée
    0.42
    Activations Density 1.372%

    No Known Activations