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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 57-GEMMASCOPE-2-TRANSCODER-262K
    4. 229369
    Prev
    Next
    INDEX
    Explanations

    ent

    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
    罗
    0.54
     ro
    0.53
    राज
    0.50
    โร
    0.50
    رو
    0.48
    रो
    0.47
    રો
    0.46
     โร
    0.46
    儸
    0.45
     roi
    0.45
    POSITIVE LOGITS
     iterations
    0.48
    ular
    0.44
    tren
    0.43
    ungkan
    0.43
     iteration
    0.42
     ት
    0.41
    fts
    0.41
    unc
    0.40
    trn
    0.40
    unen
    0.40
    Activations Density 0.000%

    No Known Activations