© 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. 3272
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific event

    oai_token-act-pair · gemini-2.0-flash

    references to events or gatherings

    np_token-act-pair-logits · gpt-4o-mini
    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
     <>",
    -0.66
    ExtendWith
    -0.65
    migrationBuilder
    -0.64
    awtextra
    -0.59
    tvguidetime
    -0.57
    bảng
    -0.56
     Bekasi
    -0.54
     StatelessWidget
    -0.53
    nościo
    -0.53
    SequentialGroup
    -0.52
    POSITIVE LOGITS
     hat
    0.57
     hats
    0.57
    IsMutable
    0.49
     something
    0.49
    λίου
    0.47
    座
    0.46
    ModelSerializer
    0.45
    podar
    0.45
    还是
    0.45
    listo
    0.45
    Activations Density 1.288%

    No Known Activations