Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 26-GEMMASCOPE-2-TRANSCODER-262K
    4. 196414
    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
    েষে
    0.47
    currentThread
    0.47
    CHREIB
    0.46
    回
    0.45
     વા
    0.44
    នុស្ស
    0.43
    DING
    0.43
    锼
    0.43
     objc
    0.43
    AVOA
    0.43
    POSITIVE LOGITS
    ="#!"
    0.44
    otas
    0.39
    zeitig
    0.38
    ieli
    0.38
    amak
    0.38
    hely
    0.38
    ifika
    0.37
     tropics
    0.37
    wash
    0.37
    pti
    0.37
    Activations Density 0.000%

    No Known Activations