© 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. 8361
    Prev
    Next
    INDEX
    Explanations

    mentions of medical procedures or concepts in scientific writing with numbers and statistics

    oai_token-act-pair · gemini-2.0-flash

    terms related to medical procedures or conditions

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

    pregnancy and medical situations

    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
     estimés
    -0.86
     дописавши
    -0.86
    rrggbb
    -0.83
    expandindo
    -0.79
    DebuggerNonUser
    -0.76
    rungsseite
    -0.75
    featureID
    -0.74
     ujednoznacz
    -0.73
     мәкал
    -0.72
    ScopeManager
    -0.70
    POSITIVE LOGITS
     transfé
    0.49
    arsch
    0.44
     McEl
    0.44
    tran
    0.43
    ans
    0.42
    GetChild
    0.42
    twin
    0.41
     Katze
    0.40
    Mc
    0.39
     twin
    0.39
    Activations Density 1.428%

    No Known Activations