© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261353
    Prev
    Next
    INDEX
    Explanations

    nympʰs and proper nouns

    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_5_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
    ו
    1.06
    ０
    1.00
    。
    0.91
    atlar
    0.87
    و
    0.85
    0
    0.84
    aloko
    0.84
    """
    0.81
    。\
    0.80
    ，
    0.80
    POSITIVE LOGITS
    n
    1.09
    ia
    1.02
    ת
    1.00
     is
    1.00
    น
    0.97
     to
    0.96
    ens
    0.96
     and
    0.94
     has
    0.93
    ン
    0.90
    Activations Density 0.000%

    No Known Activations