© 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
    2. Gemma-3-27B-IT
    3. 57-GEMMASCOPE-2-TRANSCODER-262K
    4. 229238
    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_57_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
    ariamente
    0.40
     November
    0.39
    因为它
    0.37
    驷
    0.37
     राकेश
    0.36
    Mua
    0.35
     Retrieve
    0.35
     storyteller
    0.35
     नावा
    0.35
     ट्रेन
    0.35
    POSITIVE LOGITS
     പ്രതീ
    0.36
     THRO
    0.35
    닛
    0.35
     arcu
    0.35
    𝓱
    0.34
     blonde
    0.33
     Schematic
    0.33
     fre
    0.33
     depress
    0.33
     interst
    0.33
    Activations Density 0.000%

    No Known Activations