© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37181
    Prev
    Next
    INDEX
    Explanations

    specific categories

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     pulls
    0.39
     pursuing
    0.35
    强烈
    0.35
    烈
    0.35
    烈的
    0.35
     bearded
    0.34
     pariy
    0.33
    상
    0.33
    饮
    0.33
     mainu
    0.33
    POSITIVE LOGITS
     bud
    0.54
     biom
    0.52
     republic
    0.46
     franc
    0.43
     little
    0.41
     Biom
    0.40
     afro
    0.40
     cat
    0.40
    bud
    0.40
     human
    0.39
    Activations Density 0.046%

    No Known Activations