© 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. 78594
    Prev
    Next
    INDEX
    Explanations

    pistachios and worst

    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
    ,
    1.95
     are
    1.84
    ת
    1.75
    ע
    1.65
    ри
    1.60
    ı
    1.52
    માં
    1.46
    你
    1.43
     đều
    1.39
    ی
    1.38
    POSITIVE LOGITS
    ↵
    1.44
     I
    1.42
    ch
    1.28
    ،
    1.17
    ).
    1.16
     drivetrain
    1.15
     Borneo
    1.11
     Penang
    1.10
     Polski
    1.09
     Следу
    1.09
    Activations Density 0.000%

    No Known Activations