© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108042
    Prev
    Next
    INDEX
    Explanations

    S followed by certain endings

    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_1_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
    و
    1.52
    f
    1.35
    า
    1.32
    k
    1.31
    িক
    1.28
    ம்
    1.25
    มี
    1.20
    z
    1.16
    м
    1.14
    ح
    1.09
    POSITIVE LOGITS
    I
    1.02
    IOT
    1.02
    is
    0.96
    LEN
    0.91
    IAT
    0.91
     a
    0.91
    Proble
    0.90
     Проци
    0.90
    CEL
    0.89
    dir
    0.87
    Activations Density 0.003%

    No Known Activations