© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165381
    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_13_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
    semble
    0.49
     wipe
    0.43
     kontrol
    0.41
     trattano
    0.41
     kettle
    0.41
    켓
    0.40
    REAM
    0.40
    alignParentRight
    0.40
     uko
    0.39
     BYTE
    0.39
    POSITIVE LOGITS
    ي
    0.59
    𝓎
    0.57
    ون
    0.55
    י
    0.52
    ت
    0.50
     Acknowledg
    0.50
    ك
    0.50
    ა
    0.49
     Такой
    0.49
    新加坡
    0.48
    Activations Density 0.000%

    No Known Activations