© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84905
    Prev
    Next
    INDEX
    Explanations

    play roles or control characters

    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_23_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
    master
    0.38
    pute
    0.35
    iforme
    0.35
    far
    0.34
    pad
    0.34
    gn
    0.34
    ဋ
    0.33
    rov
    0.32
    सेन
    0.32
    set
    0.32
    POSITIVE LOGITS
    ؛
    0.36
    قيم
    0.33
     비해
    0.33
     Thermodynamics
    0.31
     dibandingkan
    0.31
     Quantification
    0.31
     heml
    0.31
     opposing
    0.30
     ؛
    0.30
     مقابل
    0.30
    Activations Density 0.027%

    No Known Activations