© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91217
    Prev
    Next
    INDEX
    Explanations

    thyme

    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
    the
    0.73
    ال
    0.73
    i
    0.68
    efficients
    0.65
    an
    0.64
    ogg
    0.62
    \
    0.61
    ０
    0.60
    arounds
    0.60
    abouts
    0.59
    POSITIVE LOGITS
    ,
    0.81
    سي
    0.74
    ع
    0.70
    ל
    0.68
    ্স
    0.66
     cuenta
    0.63
     rozd
    0.63
     groe
    0.62
    سين
    0.62
     vezes
    0.61
    Activations Density 0.000%

    No Known Activations