© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58354
    Prev
    Next
    INDEX
    Explanations

    steadily increasing or improving

    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_11_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
    2
    0.95
    as
    0.86
    create
    0.84
    can
    0.84
    number
    0.83
    putting
    0.81
    var
    0.80
    F
    0.79
    void
    0.76
    W
    0.76
    POSITIVE LOGITS
     RE
    0.73
     scopo
    0.66
     ACS
    0.65
     aides
    0.65
     nods
    0.64
     YAML
    0.64
     konte
    0.64
     AL
    0.64
     isomers
    0.63
     isol
    0.63
    Activations Density 0.000%

    No Known Activations