© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22447
    Prev
    Next
    INDEX
    Explanations

    say "*"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    <unused74>
    0.29
     Temmuz
    0.29
    믄
    0.28
    䄸
    0.28
     دہشت
    0.28
     टीच
    0.27
    namefont
    0.27
     Zeits
    0.27
    iata
    0.27
     গর্
    0.26
    POSITIVE LOGITS
    |
    0.27
     code
    0.27
    AI
    0.26
     AI
    0.25
    Less
    0.25
    h
    0.25
    0.24
     a
    0.24
    p
    0.24
    Remaining
    0.24
    Activations Density 0.000%

    No Known Activations