© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248303
    Prev
    Next
    INDEX
    Explanations

    here is

    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
     tr
    0.42
    Requ
    0.38
    畢
    0.38
     Requ
    0.37
     Pu
    0.37
    Pu
    0.36
     turn
    0.35
     પુર
    0.34
     पुरु
    0.34
    çu
    0.33
    POSITIVE LOGITS
     P
    0.72
    P
    0.62
     tens
    0.56
    tens
    0.56
    可
    0.55
     pod
    0.53
     可
    0.52
     প
    0.47
    𝑃
    0.46
     П
    0.46
    Activations Density 0.001%

    No Known Activations