© 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. 196109
    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
    ر
    0.46
    ുപ
    0.46
    plied
    0.45
     voces
    0.44
    Assembly
    0.42
    ut
    0.42
    Sur
    0.41
     pihaknya
    0.41
    परेशन
    0.41
    Matched
    0.41
    POSITIVE LOGITS
     crashes
    0.49
     affects
    0.46
    에
    0.44
     Jovi
    0.41
     workouts
    0.40
     Unless
    0.40
    .",[
    0.39
    かい
    0.39
     Azerbaijani
    0.39
     Models
    0.38
    Activations Density 0.000%

    No Known Activations