© 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. 130118
    Prev
    Next
    INDEX
    Explanations

    add a section

    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
    1.29
    s
    1.29
    f
    1.12
    ad
    1.07
    ang
    1.06
    a
    1.05
    Config
    1.04
    ap
    1.03
    d
    1.02
    re
    1.02
    POSITIVE LOGITS
     distracting
    0.90
     risking
    0.88
    '
    0.86
    <0x9B>
    0.83
     robbing
    0.83
    <0xB2>
    0.82
    <0x9A>
    0.82
     meager
    0.82
    <0xAC>
    0.81
     н
    0.81
    Activations Density 0.010%

    No Known Activations