© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89489
    Prev
    Next
    INDEX
    Explanations

    java.util.List;

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    是
    1.00
    '
    0.96
    {
    0.91
    는
    0.91
    は
    0.82
    '`
    0.79
    និង
    0.74
    žení
    0.72
    {\
    0.71
    ية
    0.70
    POSITIVE LOGITS
    1.16
     tentative
    0.71
     fifteen
    0.70
    el
    0.70
     proprio
    0.68
     cameo
    0.67
     commentary
    0.63
     sweeping
    0.62
     divisor
    0.62
     tumor
    0.61
    Activations Density 0.000%

    No Known Activations