© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4725
    Prev
    Next
    INDEX
    Explanations

    the suffix "ful", and words relating to factories or history

    oai_token-act-pair · gemini-2.0-flash

    ful

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    The
    -0.78
    s
    -0.73
    ب
    -0.72
    A
    -0.70
    <h2>
    -0.69
    T
    -0.67
     tekem
    -0.67
    S
    -0.66
    <h3>
    -0.65
    G
    -0.65
    POSITIVE LOGITS
    tagHelperRunner
    0.94
    RenderAtEndOf
    0.93
    __*/
    0.90
     Zacks
    0.88
    )";
    0.88
    MemoryWarning
    0.87
     فريبيس
    0.84
    )");
    0.81
    Билгалдахарш
    0.81
    MLLoader
    0.79
    Activations Density 2.618%

    No Known Activations