© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230927
    Prev
    Next
    INDEX
    Explanations

    build new things

    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_6_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
    ב
    1.05
    د
    0.95
    То
    0.92
    รวม
    0.90
    ה
    0.90
    :
    0.89
    На
    0.86
    Р
    0.86
    ">
    0.85
            
    0.84
    POSITIVE LOGITS
    is
    1.05
    ang
    0.97
    em
    0.96
    t
    0.94
    ко
    0.94
    <0x80>
    0.92
    ка
    0.88
    ig
    0.88
    at
    0.82
    igheid
    0.80
    Activations Density 0.003%

    No Known Activations