© 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. 32258
    Prev
    Next
    INDEX
    Explanations

    1.4+ crafting terraria

    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
    ‚
    0.38
     बनाता
    0.37
    arel
    0.36
     Pool
    0.36
     Books
    0.36
    !("
    0.35
     বান
    0.35
     isla
    0.35
     português
    0.35
     ime
    0.35
    POSITIVE LOGITS
    Passenger
    0.39
     Norwood
    0.39
    வைகள்
    0.39
    軀
    0.39
     onDelete
    0.38
    یں
    0.38
    TB
    0.37
    Thor
    0.37
    {*
    0.37
    rivation
    0.37
    Activations Density 0.002%

    No Known Activations