© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32253
    Prev
    Next
    INDEX
    Explanations

    boxed latex math

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_7_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
    AR
    0.60
    AT
    0.49
    AN
    0.42
    لب
    0.39
    ar
    0.37
    <0xA0>
    0.37
    OY
    0.36
    mathbf
    0.36
    N
    0.36
    OV
    0.35
    POSITIVE LOGITS
     be
    0.71
     in
    0.67
     can
    0.59
     for
    0.59
     increase
    0.57
     not
    0.57
     improve
    0.54
    이지만
    0.54
     has
    0.53
     deny
    0.53
    Activations Density 0.001%

    No Known Activations