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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 26-GEMMASCOPE-2-TRANSCODER-262K
    4. 195838
    Prev
    Next
    INDEX
    Explanations

    special prices or offers

    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_26_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
     leftWheel
    0.55
     procent
    0.55
    glRaster
    0.52
    肦
    0.52
     بە
    0.51
     Associ
    0.50
     associ
    0.50
     _$
    0.50
    बंधनाच्या
    0.49
     തിരഞ്ഞെടു
    0.48
    POSITIVE LOGITS
    (
    0.51
    Hollywood
    0.49
    Created
    0.48
    PET
    0.47
    ED
    0.46
    Urban
    0.45
    У
    0.45
    Lessons
    0.45
    Prairie
    0.45
    Episode
    0.44
    Activations Density 0.000%

    No Known Activations