© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130492
    Prev
    Next
    INDEX
    Explanations

    you'll use

    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_25_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
     steel
    0.32
     carries
    0.32
     artisan
    0.32
     Steel
    0.32
     C
    0.31
     exceptions
    0.31
    Steel
    0.31
     Exceptions
    0.31
     Street
    0.31
     Qu
    0.30
    POSITIVE LOGITS
    зербайд
    0.43
    urschutz
    0.39
     gesehen
    0.38
     思う
    0.37
     necessária
    0.36
    쌓
    0.34
    ឡិចត្រូ
    0.34
    äude
    0.34
    oljš
    0.34
    ́ch
    0.33
    Activations Density 0.011%

    No Known Activations