© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223421
    Prev
    Next
    INDEX
    Explanations

    links with question marks

    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_10_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
    ﻛ
    0.79
    ﭼ
    0.77
    да
    0.75
    izarea
    0.73
    は
    0.73
     beverages
    0.72
    카페
    0.72
    ла
    0.71
    に使
    0.71
    '
    0.70
    POSITIVE LOGITS
    on
    0.84
     to
    0.84
    an
    0.81
    a
    0.81
    all
    0.81
    ه
    0.79
    ry
    0.79
    lent
    0.77
    man
    0.76
    oretically
    0.76
    Activations Density 0.001%

    No Known Activations