© 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. 196039
    Prev
    Next
    INDEX
    Explanations

    `error` followed by `Scul` or `)`

    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
    eOut
    0.47
    گران
    0.45
    שו
    0.44
    quero
    0.44
    ై
    0.42
     Maio
    0.42
    ة
    0.41
    ся
    0.40
    ijn
    0.40
     کیا۔
    0.39
    POSITIVE LOGITS
     battlefield
    0.40
     aujourd
    0.38
     meski
    0.38
     kag
    0.38
     процесс
    0.37
     ct
    0.37
     Battlefield
    0.37
    -'+
    0.36
     stillness
    0.36
     seterusnya
    0.35
    Activations Density 0.000%

    No Known Activations