© 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. 197040
    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
     banheiro
    0.48
     vaak
    0.42
    繆
    0.41
     глаза
    0.41
    माजिक
    0.40
     جام
    0.40
     нару
    0.40
     สัก
    0.40
     internos
    0.40
     ጊዜ
    0.39
    POSITIVE LOGITS
    ̣
    0.46
     Ch
    0.42
     Change
    0.39
     contexts
    0.37
     democratic
    0.35
    ̀i
    0.34
     offerings
    0.34
     Preserve
    0.34
     appetite
    0.34
    ̀
    0.34
    Activations Density 0.000%

    No Known Activations