© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 197018
    Prev
    Next
    INDEX
    Explanations

    syntax errors

    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
    א
    0.55
    ла
    0.51
    ін
    0.47
    マ
    0.46
    Argentina
    0.44
    IN
    0.43
    lenme
    0.43
    Madison
    0.42
     ސ
    0.42
    ﯾ
    0.42
    POSITIVE LOGITS
     ३
    0.50
    
    0.46
     eigener
    0.45
     bekend
    0.45
    哴
    0.45
     modell
    0.44
     Kae
    0.44
     gris
    0.44
     snuff
    0.43
     islands
    0.42
    Activations Density 0.000%

    No Known Activations