© 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
    2. Gemma-3-27B-IT
    3. 26-GEMMASCOPE-2-TRANSCODER-262K
    4. 196285
    Prev
    Next
    INDEX
    Explanations

    URL patterns

    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_26_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
    3
    0.39
    inig
    0.38
     रोशनी
    0.37
     각
    0.37
    ถือ
    0.36
    jj
    0.34
    Sure
    0.34
     uu
    0.33
    軺
    0.33
     Out
    0.33
    POSITIVE LOGITS
     symmetrically
    0.46
     شیطان
    0.46
     ditth
    0.45
     imassa
    0.45
     natthi
    0.44
     veniam
    0.44
     przedsi
    0.43
     imprese
    0.43
     attham
    0.43
     sécr
    0.43
    Activations Density 0.000%

    No Known Activations