© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39694
    Prev
    Next
    INDEX
    Explanations

    initialisms

    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_57_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
     B
    0.67
     D
    0.66
     C
    0.59
     P
    0.56
     S
    0.54
     H
    0.54
     M
    0.53
     Q
    0.52
     J
    0.52
     E
    0.51
    POSITIVE LOGITS
     DC
    0.77
     JD
    0.70
     JS
    0.69
     JC
    0.68
     BC
    0.68
     BS
    0.67
     JP
    0.66
    DC
    0.66
     JK
    0.66
     JA
    0.65
    Activations Density 0.026%

    No Known Activations