© 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. 37162
    Prev
    Next
    INDEX
    Explanations

    how long

    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
    Type
    0.82
    is
    0.79
    ?
    0.74
    ">
    0.70
     It
    0.66
    0
    0.66
    "
    0.64
    Time
    0.63
    Value
    0.63
    orithm
    0.62
    POSITIVE LOGITS
    н
    0.95
    นี
    0.77
    ν
    0.71
     flops
    0.68
    น
    0.68
    เป็น
    0.66
    க்
    0.64
    ποίηση
    0.64
     которое
    0.62
     baixo
    0.61
    Activations Density 0.003%

    No Known Activations