© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 130534
    Prev
    Next
    INDEX
    Explanations

    .*

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
    亙
    0.30
     nonequilibrium
    0.28
     कोणता
    0.26
    благо
    0.25
     Finnish
    0.25
    ുകളില്‍
    0.24
     Hesse
    0.23
     mida
    0.23
    亘
    0.23
    льном
    0.23
    POSITIVE LOGITS
     reforzar
    0.26
    LIK
    0.26
    福
    0.25
     విధంగా
    0.25
    FU
    0.24
    Noah
    0.23
     reinforcing
    0.23
     reinforcements
    0.23
    dı
    0.23
     Pfarr
    0.22
    Activations Density 0.007%

    No Known Activations