© 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
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167089
    Prev
    Next
    INDEX
    Explanations

    recommendations

    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_56_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
     su
    3.22
     су
    2.64
     Su
    2.56
    Su
    2.47
    su
    2.36
    苏
    2.05
     سو
    2.03
     सु
    1.95
    蘇
    1.77
     সু
    1.69
    POSITIVE LOGITS
    nsp
    0.39
    幹
    0.38
    ằ
    0.38
     UIT
    0.36
    ণিত
    0.36
    oconvex
    0.35
    렴
    0.35
     เหมาะ
    0.34
     briefcase
    0.34
     fits
    0.33
    Activations Density 0.003%

    No Known Activations