© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16975
    Prev
    Next
    INDEX
    Explanations

    tac

    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_15_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
    <unused2141>
    0.22
     undermines
    0.20
    ləş
    0.19
    +{\
    0.18
     dispositivi
    0.18
     monotonically
    0.18
     pluripotent
    0.18
     itiner
    0.18
    citenamefont
    0.18
     Ull
    0.18
    POSITIVE LOGITS
    ر
    0.25
    ض
    0.23
    ري
    0.21
    Michigan
    0.20
    패
    0.20
    تنا
    0.20
    Poker
    0.20
    ره
    0.19
    ров
    0.19
    Roberts
    0.19
    Activations Density 0.007%

    No Known Activations