© 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. 9413
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and codes.

    oai_token-act-pair · gemini-2.0-flash

    terms related to funding and educational initiatives

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

    state legal documents

    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
     state
    -2.17
     states
    -1.95
    state
    -1.94
     State
    -1.80
     STATE
    -1.73
    State
    -1.71
    states
    -1.70
    STATE
    -1.66
     States
    -1.55
    States
    -1.55
    POSITIVE LOGITS
    expandindo
    0.80
    PreferredItem
    0.70
     виправивши
    0.63
     autorytatywna
    0.59
     estekak
    0.57
     BIBSYS
    0.56
     SUDOC
    0.56
     فريبيس
    0.56
     ddelweddau
    0.56
    الدراسه
    0.55
    Activations Density 2.102%

    No Known Activations