© 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. 6960
    Prev
    Next
    INDEX
    Explanations

    mentions of state and models

    oai_token-act-pair · gemini-2.0-flash

    terms related to database states and management

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

    state

    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
    Personensuche
    -0.63
    ंदीखरीदारी
    -0.60
     المعيارى
    -0.51
     createState
    -0.49
    state
    -0.48
    nanoTime
    -0.48
    ndham
    -0.46
     useState
    -0.46
    actrice
    -0.46
     state
    -0.46
    POSITIVE LOGITS
    MLLoader
    0.63
     Abo
    0.57
    IZI
    0.56
    Personendaten
    0.56
    ormon
    0.54
     purpure
    0.52
    OMC
    0.52
    Smarty
    0.52
    AndEndTag
    0.51
    migrationBuilder
    0.51
    Activations Density 5.785%

    No Known Activations