© 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. 130118
    Prev
    Next
    INDEX
    Explanations

    patsy, atcher, atter

    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
     in
    1.20
     It
    0.97
    0
    0.93
     The
    0.90
    <0x80>
    0.89
    ре
    0.86
     Were
    0.85
    č
    0.82
     ০
    0.81
     এরপর
    0.80
    POSITIVE LOGITS
    로
    1.35
    '
    1.19
    ur
    1.15
     shameful
    1.10
    to
    1.05
    ’
    1.05
     destacados
    1.04
    ست
    1.03
    हरु
    1.03
    -
    1.03
    Activations Density 0.000%

    No Known Activations