© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4284
    Prev
    Next
    INDEX
    Explanations

    mentions of "first" and then things that might plausibly be connected to being first, and also satnavs

    oai_token-act-pair · gemini-2.0-flash

    Maps and navigation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    +#+#
    -0.66
    tagHelperRunner
    -0.57
    FlatList
    -0.55
    mės
    -0.50
     الاطلاع
    -0.49
    ItemGroup
    -0.47
     cur
    -0.46
    multer
    -0.46
     calendriers
    -0.46
    gäng
    -0.45
    POSITIVE LOGITS
    Autoritní
    0.61
    FontOfSize
    0.59
    blink
    0.59
     autorytatywna
    0.54
     texinfo
    0.54
     micro
    0.54
     spikes
    0.53
    principalColumn
    0.53
    vdash
    0.52
    NewGuid
    0.52
    Activations Density 1.484%

    No Known Activations