© 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. 133777
    Prev
    Next
    INDEX
    Explanations

    insert mode prefixes

    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
    an
    1.51
    h
    1.33
    as
    1.30
    on
    1.26
    n
    1.14
    ת
    1.13
    ان
    1.10
    to
    1.09
    at
    1.08
    ed
    1.07
    POSITIVE LOGITS
    I
    1.15
     I
    0.94
    (
    0.89
    IS
    0.77
    在
    0.77
     Espí
    0.75
     \
    0.75
    »
    0.74
    <0x80>
    0.73
    <0xBF>
    0.71
    Activations Density 0.000%

    No Known Activations