© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137869
    Prev
    Next
    INDEX
    Explanations

    API and technical jargon

    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_12_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
    Corollary
    0.40
    ↵
    0.39
    achar
    0.39
    verso
    0.39
     avert
    0.37
    鄞
    0.37
    ulae
    0.36
    même
    0.35
    keycode
    0.35
     Temper
    0.35
    POSITIVE LOGITS
    د
    0.50
    ન
    0.44
    Ն
    0.44
    ’
    0.43
     largest
    0.43
    из
    0.42
    แหล่ง
    0.41
    پ
    0.41
    ల
    0.41
    小麦
    0.41
    Activations Density 0.008%

    No Known Activations