© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175355
    Prev
    Next
    INDEX
    Explanations

    HTML `tbody` tags

    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_24_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
    il
    0.49
     Manor
    0.45
     सही
    0.44
    ilie
    0.44
    i
    0.43
    ont
    0.42
    isations
    0.42
    uen
    0.41
     Slide
    0.41
    slide
    0.41
    POSITIVE LOGITS
    杣
    0.53
    гъл
    0.52
    در
    0.50
    غيرة
    0.50
    ግባ
    0.48
    زوج
    0.46
    élevage
    0.46
    ProfileAction
    0.46
    Lapangan
    0.46
     estén
    0.46
    Activations Density 0.000%

    No Known Activations