© 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. 2667
    Prev
    Next
    INDEX
    Explanations

    code with hexadecimal values, bracketed expressions, and parenthesis

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     utafitiHapana
    -0.91
    makeConstraints
    -0.88
    Rüyada
    -0.86
     <<<<<<<<<<<<<<
    -0.85
    NameInMap
    -0.84
     externi
    -0.83
    ArrowToggle
    -0.78
     ویکی‌پدیای
    -0.77
    EndContext
    -0.76
    INCREF
    -0.76
    POSITIVE LOGITS
    <bos>
    1.15
     and
    0.49
    ,
    0.45
     it
    0.41
    </
    0.41
    ern
    0.41
    :</
    0.41
    we
    0.41
    ."</
    0.40
    ↵
    0.40
    Activations Density 2.099%

    No Known Activations