© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 203104
    Prev
    Next
    INDEX
    Explanations

    running or false state

    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
    Negative Logits
    新的
    0.46
     nuova
    0.44
     নতুন
    0.43
     Fay
    0.43
    atom
    0.41
    ard
    0.40
    hat
    0.40
    ~)
    0.40
    new
    0.40
     novos
    0.39
    POSITIVE LOGITS
    Popul
    0.43
    णाली
    0.42
     beginnetje
    0.39
    MediaPath
    0.38
     Popul
    0.38
     spurious
    0.38
    พื้น
    0.38
    LookAnd
    0.37
    ającym
    0.37
    ಿಂತ
    0.37
    Activations Density 0.001%

    No Known Activations