© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 164925
    Prev
    Next
    INDEX
    Explanations

    limit h->0 or w

    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_13_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
    raving
    0.31
    тельство
    0.31
    тому
    0.31
    itié
    0.30
    JSONException
    0.30
    ppard
    0.30
     prisión
    0.30
    啰
    0.30
     loaned
    0.29
     마치
    0.29
    POSITIVE LOGITS
    ก
    0.42
    g
    0.40
    К
    0.40
    크
    0.38
     ادار
    0.36
    ગ
    0.36
     établ
    0.35
     অক্সিজ
    0.35
     acetone
    0.35
    tipo
    0.35
    Activations Density 0.014%

    No Known Activations