© 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-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142115
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    érrez
    0.50
     రూప
    0.48
     తగ్గ
    0.48
    తున్నారు
    0.47
    ácia
    0.46
     መስ
    0.46
    <unused187>
    0.46
    幵
    0.46
    🛒
    0.46
    స్తున్నారు
    0.46
    POSITIVE LOGITS
    0.59
    g
    0.55
    ک
    0.55
    나
    0.54
    voltage
    0.47
     a
    0.46
    adjust
    0.46
    b
    0.46
    お
    0.45
     deuter
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.