© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51919
    Prev
    Next
    INDEX
    Explanations

    event details

    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_31_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
     osl
    0.39
     demean
    0.37
     rozm
    0.36
    طانیہ
    0.36
    溂
    0.36
     Paine
    0.35
    ್ಟ
    0.34
    <unused400>
    0.34
     obes
    0.34
    ErrorInfo
    0.34
    POSITIVE LOGITS
    캔
    0.42
    星期
    0.39
     GLASS
    0.39
     адресу
    0.37
    Venue
    0.37
     촬영
    0.37
     TRANSP
    0.37
     ಪ್ಯಾ
    0.36
    Á
    0.36
    储存
    0.36
    Activations Density 0.000%

    No Known Activations