© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14005
    Prev
    Next
    INDEX
    Explanations

    names of people, especially officials or criminals, and words pertaining to legal situations

    oai_token-act-pair · gemini-2.0-flash

    South African legal cases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     minh
    -0.52
    addGap
    -0.50
     Karp
    -0.48
     Schuld
    -0.48
     gates
    -0.47
    ۪
    -0.47
     quoc
    -0.46
    inerary
    -0.46
    Lemon
    -0.46
    navigationItem
    -0.45
    POSITIVE LOGITS
    setVerticalGroup
    0.71
     kasarigan
    0.71
    \{\\
    0.69
     autorytatywna
    0.66
     跳转至
    0.64
     GetEnumerator
    0.58
    IsMutable
    0.58
    providedIn
    0.58
     resourceCulture
    0.58
     TextAlign
    0.57
    Activations Density 0.396%

    No Known Activations