© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109904
    Prev
    Next
    INDEX
    Explanations

    clear out corrupted or stale

    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
    л
    1.88
    ס
    1.79
    ל
    1.39
    ل
    1.34
    ד
    1.34
    ש
    1.34
    н
    1.23
    ר
    1.23
    ล
    1.12
    な
    1.09
    POSITIVE LOGITS
    </h3>
    1.00
    hwa
    0.95
    t
    0.95
    ok
    0.89
    tól
    0.87
    okas
    0.85
    ación
    0.84
    ikleri
    0.82
    ablo
    0.82
    afar
    0.81
    Activations Density 0.000%

    No Known Activations