© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165347
    Prev
    Next
    INDEX
    Explanations

    express, qualification, vertical

    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_13_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
    чил
    0.49
    ла
    0.48
    awca
    0.46
    m
    0.43
    摑
    0.43
    нка
    0.42
    ascus
    0.41
     alternately
    0.41
     segmented
    0.39
    many
    0.38
    POSITIVE LOGITS
    StudentNo
    0.51
     ont
    0.50
     antide
    0.49
    otype
    0.48
     prologue
    0.46
     inizia
    0.46
     nupt
    0.46
    Stat
    0.46
    牍
    0.46
    ផល
    0.46
    Activations Density 0.000%

    No Known Activations