© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80520
    Prev
    Next
    INDEX
    Explanations

    satisfies certain conditions

    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_0_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
    ın
    2.34
    কে
    2.09
    é
    1.94
    '
    1.93
    та
    1.91
     are
    1.67
    ের
    1.65
    -
    1.63
    _
    1.61
     can
    1.60
    POSITIVE LOGITS
    L
    1.71
    S
    1.32
    К
    1.27
    ről
    1.27
    G
    1.15
    D
    1.09
     在
    1.06
    做
    1.06
    全球
    1.05
    zhang
    1.05
    Activations Density 0.003%

    No Known Activations