© 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. 196124
    Prev
    Next
    INDEX
    Explanations

    configuration and route building

    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
    اخ
    0.42
     yên
    0.39
    TRUE
    0.39
     질
    0.38
    אס
    0.38
     کیلئے
    0.37
    र्वे
    0.37
    ુદ્ધ
    0.35
    ಲೆಂ
    0.34
     बरत
    0.34
    POSITIVE LOGITS
     sonucu
    0.46
     frivol
    0.43
    ponenten
    0.43
    /
    0.42
    рый
    0.41
    <0x0D>
    0.41
     stør
    0.38
    *{\
    0.38
     Redeem
    0.37
    keny
    0.37
    Activations Density 0.000%

    No Known Activations