© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63339
    Prev
    Next
    INDEX
    Explanations

    2

    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_46_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
    writeInt
    0.39
    peaks
    0.38
    mf
    0.36
    )\|_{\
    0.36
    PURE
    0.35
    proof
    0.34
    pure
    0.34
    offensive
    0.34
    fler
    0.34
     Buy
    0.34
    POSITIVE LOGITS
     कार्या
    0.43
     Zapata
    0.42
     VCS
    0.40
    цца
    0.40
    穷
    0.40
     faucet
    0.39
     निजामा
    0.39
     kya
    0.39
     DETERMIN
    0.38
    父母
    0.38
    Activations Density 0.001%

    No Known Activations