© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83004
    Prev
    Next
    INDEX
    Explanations

    optimism

    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
    '
    1.65
    {
    1.38
    €™
    1.34
    _
    1.33
    K
    1.30
    Y
    1.30
    ס
    1.30
    }
    1.27
    ﾞ
    1.27
    AR
    1.22
    POSITIVE LOGITS
    is
    1.68
    ación
    1.67
    し
    1.63
    ৫
    1.45
    ل
    1.41
    ia
    1.33
    lük
    1.33
    ett
    1.29
    보
    1.25
    га
    1.23
    Activations Density 0.001%

    No Known Activations