© 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. 39415
    Prev
    Next
    INDEX
    Explanations

    code symbols

    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
     처
    0.45
    _:
    0.39
    _{+}^{
    0.38
     Thousand
    0.36
     baseball
    0.36
    喱
    0.36
     housing
    0.35
     mutant
    0.35
     gil
    0.35
    _(
    0.35
    POSITIVE LOGITS
    (-
    1.16
     (-
    1.11
     $(-
    1.11
     $-
    1.03
    }(-
    1.02
     (−
    1.02
    (−
    0.98
     =-
    0.97
     −
    0.96
    }}(-
    0.94
    Activations Density 0.080%

    No Known Activations