© 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. 10086
    Prev
    Next
    INDEX
    Explanations

    words related to electrical impulses and signalling

    oai_token-act-pair · gemini-2.0-flash

    pulses, beams

    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
    )");
    -0.64
     referenties
    -0.63
    )');
    -0.62
    ?')
    -0.56
    ership
    -0.56
    [])
    -0.56
    stb
    -0.54
    клопе
    -0.54
    zość
    -0.54
     sito
    -0.53
    POSITIVE LOGITS
     Exactos
    0.58
    <bos>
    0.58
     виправивши
    0.55
    
    0.54
    bewerken
    0.52
    MessageInfo
    0.50
    migrationBuilder
    0.50
    StartTag
    0.49
    WithIOException
    0.49
    Datuak
    0.48
    Activations Density 1.980%

    No Known Activations