© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130260
    Prev
    Next
    INDEX
    Explanations

    obtained through

    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
    {
    1.16
    ف
    1.09
    л
    1.07
    ל
    1.05
    ल
    1.04
    T
    1.02
    通过
    1.02
    ل
    1.01
    ב
    1.01
     to
    0.97
    POSITIVE LOGITS
    <0xBE>
    0.86
    ﺖ
    0.84
     who
    0.82
     মধ্যে
    0.82
    ல்
    0.81
     faixa
    0.81
    ни
    0.75
    ми
    0.75
     furry
    0.74
     venenatis
    0.74
    Activations Density 0.003%

    No Known Activations