© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    4. 228447
    Prev
    Next
    INDEX
    Explanations

    neutrino

    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
    VISION
    0.43
    PPAR
    0.43
    rafts
    0.42
    蝰
    0.42
    Wol
    0.40
    chol
    0.39
     RAR
    0.38
    Rib
    0.38
    బీ
    0.38
    olaire
    0.38
    POSITIVE LOGITS
    or
    0.41
    res
    0.41
    r
    0.39
     Ten
    0.38
     Ela
    0.38
     mental
    0.37
    惮
    0.37
     credential
    0.37
    ร
    0.37
    h
    0.36
    Activations Density 0.000%

    No Known Activations