© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212888
    Prev
    Next
    INDEX
    Explanations

    Snake Plissken regressionAccounts

    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
    自己
    0.86
    」
    0.84
    ))
    0.83
    ’
    0.80
    N
    0.78
    B
    0.75
     inici
    0.73
    t
    0.73
    F
    0.73
    determ
    0.71
    POSITIVE LOGITS
    ла
    1.61
    ק
    1.30
    на
    1.28
    ia
    1.14
    ہ
    1.13
    ك
    1.09
    ம்
    1.06
    น
    1.05
    ad
    1.04
    id
    1.01
    Activations Density 0.000%

    No Known Activations