© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 166962
    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_56_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
    自
    0.76
    Self
    0.68
     self
    0.67
     Self
    0.65
    self
    0.57
     SELF
    0.57
     tự
    0.55
    も
    0.53
    Само
    0.50
     zelf
    0.49
    POSITIVE LOGITS
     dhad
    0.37
    stava
    0.36
     ifelse
    0.34
    సం
    0.34
     ہاتھوں
    0.33
     சார்ப
    0.33
    衾
    0.33
     Carpathians
    0.33
    графии
    0.32
     Wahr
    0.32
    Activations Density 0.000%

    No Known Activations