© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234744
    Prev
    Next
    INDEX
    Explanations

    programming code punctuation

    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_32_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
    Supreme
    0.34
     red
    0.33
     active
    0.33
     Uh
    0.33
     scolded
    0.33
    红
    0.32
     persecuted
    0.31
     action
    0.30
    ajima
    0.30
     seismic
    0.29
    POSITIVE LOGITS
    )'=='
    0.35
    Charting
    0.34
    ))$
    0.33
    ubjects
    0.32
     として
    0.32
    殺
    0.31
    বিষয়
    0.31
    heur
    0.31
    AndKeys
    0.31
    ))$,
    0.31
    Activations Density 0.007%

    No Known Activations