© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11784
    Prev
    Next
    INDEX
    Explanations

    last names

    oai_token-act-pair · gemini-2.0-flash

    legal/scientific texts, names

    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
    ">//
    -0.81
    FunctionFlags
    -0.72
    +#+#
    -0.72
    jooq
    -0.71
     intptr
    -0.71
    IntoConstraints
    -0.69
    Abit
    -0.69
     defaultstate
    -0.68
     تانيه
    -0.66
     morire
    -0.66
    POSITIVE LOGITS
     Irish
    0.64
     Hiber
    0.55
     Murphy
    0.54
     Ireland
    0.54
    digan
    0.53
     Kilkenny
    0.52
    Murphy
    0.50
     Ronan
    0.50
    Irish
    0.49
     irish
    0.49
    Activations Density 0.375%

    No Known Activations