© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5455
    Prev
    Next
    INDEX
    Explanations

    melee weapon, robust online, insult swordfight

    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
     handover
    0.43
    FixedHeight
    0.40
    CellStyle
    0.38
     cellular
    0.37
     vállalat
    0.37
     Cellular
    0.36
    动
    0.36
     ಆದ
    0.35
    ответ
    0.35
     Handwriting
    0.35
    POSITIVE LOGITS
    Armor
    0.44
     AI
    0.43
     rendering
    0.43
    AI
    0.42
    lez
    0.42
     armor
    0.42
     অনলাইন
    0.42
     renderings
    0.42
    Collision
    0.41
    Bonus
    0.41
    Activations Density 0.178%

    No Known Activations