© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13932
    Prev
    Next
    INDEX
    Explanations

    Better + service/company name

    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_40_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
     kol
    0.37
     Ranger
    0.36
     stable
    0.36
    尺
    0.36
    azon
    0.36
    Stable
    0.36
     plaid
    0.35
    ¸
    0.35
     kh
    0.35
     Stable
    0.35
    POSITIVE LOGITS
    imbangkan
    0.38
    㳯
    0.38
    াপন
    0.37
    Brows
    0.37
    ্কৃত
    0.37
    oxidation
    0.37
    ઓએ
    0.37
     Bisa
    0.37
    ewomen
    0.36
    τικ
    0.36
    Activations Density 0.001%

    No Known Activations