© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12880
    Prev
    Next
    INDEX
    Explanations

    words and concepts related to computer science and data analysis

    oai_token-act-pair · gemini-2.0-flash

    terms related to digital security and authentication

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

    Foreign words

    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
     становника
    -0.79
    BASEPATH
    -0.63
    StoreMessageInfo
    -0.59
    NUMX
    -0.57
    antMatchers
    -0.57
     getItemId
    -0.56
     tuong
    -0.55
     contextLoads
    -0.54
    EndGlobalSection
    -0.53
    SPATH
    -0.52
    POSITIVE LOGITS
    ógicas
    0.53
    Hozzáférés
    0.51
    olí
    0.50
    timewa
    0.49
    Xna
    0.49
    lible
    0.45
    ógicos
    0.44
    批
    0.44
     stock
    0.44
    rungsseite
    0.44
    Activations Density 2.746%

    No Known Activations