© 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
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106417
    Prev
    Next
    INDEX
    Explanations

    repetition

    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_1_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
    ם
    1.43
    ו
    1.05
    ٦
    0.95
    ט
    0.94
    ן
    0.91
    ।]
    0.91
    ፕሮ
    0.89
    
    0.89
    ל
    0.89
    ת
    0.88
    POSITIVE LOGITS
     of
    1.50
     at
    1.45
     to
    1.23
     and
    1.11
    O
    1.08
     on
    1.04
    of
    1.04
    On
    0.98
     lineman
    0.98
     that
    0.97
    Activations Density 0.002%

    No Known Activations