© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210644
    Prev
    Next
    INDEX
    Explanations

    page number and steps

    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_5_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
    ’
    1.60
    。
    0.88
    ’”
    0.86
    )’
    0.85
    ’;
    0.80
     materna
    0.80
    RU
    0.79
     Cabernet
    0.79
     konfer
    0.79
     ILO
    0.79
    POSITIVE LOGITS
    a
    1.38
    s
    1.24
    る
    1.20
    ت
    1.16
    ك
    1.11
    ה
    1.03
    고
    0.98
    ன்
    0.97
     a
    0.96
    ی
    0.95
    Activations Density 0.014%

    No Known Activations