© 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
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-TRANSCODER-262K
    4. 79751
    Prev
    Next
    INDEX
    Explanations

    actions and events

    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_53_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
    enza
    0.40
     मद्देनजर
    0.40
    BS
    0.39
    ährung
    0.39
    (...
    0.38
     ঝ
    0.38
    izan
    0.37
    يله
    0.36
    贻
    0.36
    MS
    0.36
    POSITIVE LOGITS
     gesch
    1.74
    gesch
    1.27
     Gesch
    1.20
    Gesch
    1.10
     ges
    0.95
     ske
    0.73
     happened
    0.68
     happens
    0.64
     Hist
    0.63
     történ
    0.61
    Activations Density 0.001%

    No Known Activations