© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229272
    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
     Sp
    0.61
    Sp
    0.57
    Ap
    0.54
     Ap
    0.53
     sp
    0.47
     Et
    0.44
     C
    0.43
    C
    0.40
     Spi
    0.40
     Rp
    0.39
    POSITIVE LOGITS
     dicen
    0.39
     nave
    0.38
     soie
    0.37
     pele
    0.36
     아마
    0.36
     guardian
    0.36
     nuevos
    0.36
     persian
    0.36
     ड्रीम
    0.35
    푥
    0.35
    Activations Density 0.000%

    No Known Activations