© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11234
    Prev
    Next
    INDEX
    Explanations

    code punctuation such as semicolons, periods, asterisks, slashes, and comment markers

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    .
    -1.23
    ?
    -1.04
     resourceCulture
    -0.97
     الحره
    -0.96
    !
    -0.94
    :
    -0.91
    *
    -0.87
     .
    -0.83
    TagMode
    -0.82
    _
    -0.82
    POSITIVE LOGITS
    OOT
    0.43
     *
    0.43
    IRM
    0.41
     Meanwhile
    0.40
    旋
    0.40
    <eos>
    0.39
    Meanwhile
    0.39
    ↵↵
    0.39
    ouch
    0.39
     
    0.38
    Activations Density 2.882%

    No Known Activations