© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54764
    Prev
    Next
    INDEX
    Explanations

    units of time since

    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_30_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
     AI
    0.37
    ]}
    0.37
    ्न
    0.36
    Visit
    0.36
     bilan
    0.36
    clap
    0.35
     Lect
    0.35
    To
    0.35
    AI
    0.35
    *:
    0.34
    POSITIVE LOGITS
     sejak
    0.46
    ตั้งแต่
    0.46
     since
    0.42
    since
    0.41
     waarin
    0.40
    neutrophiles
    0.40
     gehalten
    0.39
     desde
    0.39
    gebracht
    0.39
     auxquelles
    0.39
    Activations Density 0.002%

    No Known Activations