© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161226
    Prev
    Next
    INDEX
    Explanations

    Keq, Kefka, Kemet, Kearns, Qué

    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_2_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
    on
    1.38
    stile
    1.31
     on
    1.26
    st
    1.16
     in
    1.14
    in
    1.12
     s
    1.10
    does
    1.08
    ového
    1.07
    don
    1.06
    POSITIVE LOGITS
    (
    1.79
    <0x80>
    1.59
    ные
    1.42
    י
    1.37
    اری
    1.34
    '
    1.31
    یم
    1.20
    ا
    1.19
    ם
    1.16
    \
    1.15
    Activations Density 0.000%

    No Known Activations