© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2255
    Prev
    Next
    INDEX
    Explanations

    code diffs with line numbers and additions

    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_39_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
     मार्गों
    0.44
    ッカ
    0.41
     স্ট্যান্ড
    0.40
    astico
    0.39
    邝
    0.38
    CONSOLE
    0.38
     প্রয়োজনীয়
    0.38
    tempCard
    0.38
    સભા
    0.38
    ꒷
    0.37
    POSITIVE LOGITS
     where
    0.44
     где
    0.41
     حيث
    0.38
     invasions
    0.38
     invasion
    0.37
     مس
    0.37
     time
    0.36
     secretly
    0.36
     nightmares
    0.36
     où
    0.35
    Activations Density 0.000%

    No Known Activations