© 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. 130549
    Prev
    Next
    INDEX
    Explanations

    best in future

    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
    ewall
    0.42
    normalize
    0.42
    slice
    0.38
    riminate
    0.37
    သည့်
    0.36
    plicate
    0.36
    緩
    0.36
    ewise
    0.36
     ایسا
    0.35
     doigts
    0.34
    POSITIVE LOGITS
     corporate
    0.50
    corporate
    0.41
     Испа
    0.41
    雫
    0.41
    Corporate
    0.40
     corporates
    0.39
     Corporate
    0.39
    ភាព
    0.38
     begrü
    0.38
     शाही
    0.38
    Activations Density 0.002%

    No Known Activations