© 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. 196151
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     الب
    0.44
     has
    0.43
     que
    0.41
     മാ
    0.40
     ලෙස
    0.40
     că
    0.40
     목
    0.40
     B
    0.39
     Turt
    0.39
    マ
    0.38
    POSITIVE LOGITS
     Wills
    0.44
     availed
    0.43
     wills
    0.43
     decommission
    0.41
    ज्ञान
    0.40
    ौली
    0.40
     eszk
    0.40
    🖇
    0.40
     immun
    0.39
     ATMs
    0.39
    Activations Density 0.000%

    No Known Activations