© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 145520
    Prev
    Next
    INDEX
    Explanations

    project structure directories

    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_18_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
    supported
    0.50
     supported
    0.49
    cast
    0.48
    station
    0.48
    et
    0.47
    of
    0.46
     Oaks
    0.46
    E
    0.45
    in
    0.45
    ir
    0.45
    POSITIVE LOGITS
     phospholipids
    0.49
     leftWheel
    0.46
     caloric
    0.45
     enzymes
    0.44
     organismes
    0.44
     euclidean
    0.44
     うる
    0.43
     halfCanvas
    0.43
     bactéri
    0.43
     tarses
    0.42
    Activations Density 0.004%

    No Known Activations