© 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. 227451
    Prev
    Next
    INDEX
    Explanations

    MS-ID identifiers

    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
    ým
    0.86
     zařízení
    0.83
    嘏
    0.82
     electrón
    0.79
     automático
    0.79
     камер
    0.79
     histórica
    0.78
    ش
    0.76
    த்தில்
    0.75
    iéndose
    0.75
    POSITIVE LOGITS
     be
    1.60
    {
    1.46
    (
    1.30
    L
    1.16
    \
    1.16
     you
    1.13
    &
    1.11
    $
    1.08
     a
    1.05
    ا
    1.05
    Activations Density 0.000%

    No Known Activations