© 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. 232228
    Prev
    Next
    INDEX
    Explanations

    representatives and examiners

    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
    ၊
    0.90
    infodisc
    0.80
    ნდა
    0.78
    களில்
    0.75
    ro
    0.75
    cht
    0.74
     faiblement
    0.73
    мб
    0.73
     অঞ্চলে
    0.72
    '،
    0.71
    POSITIVE LOGITS
    .
    1.42
     .
    0.93
    t
    0.91
     $
    0.89
     is
    0.83
     of
    0.80
    ↵
    0.78
    לי
    0.74
    \
    0.74
    ong
    0.73
    Activations Density 0.000%

    No Known Activations