© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2660
    Prev
    Next
    INDEX
    Explanations

    scientific writing and related ideas

    oai_token-act-pair · gemini-2.0-flash

    tic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     soul
    -0.76
     souls
    -0.62
     foreign
    -0.57
    soul
    -0.54
     Soul
    -0.54
    Foreign
    -0.53
    foreign
    -0.53
    Soul
    -0.52
     Foreign
    -0.51
     innovation
    -0.50
    POSITIVE LOGITS
    contentLoaded
    0.89
    rungsseite
    0.64
    ]--;
    0.64
    +#+
    0.62
    دانشنامهٔ
    0.60
    ьажоргаш
    0.60
    WireFormatLite
    0.59
    thâu
    0.56
     Balla
    0.56
     ExecuteAsync
    0.56
    Activations Density 12.842%

    No Known Activations