© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206523
    Prev
    Next
    INDEX
    Explanations

    angle, notation, angle

    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_10_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
    c
    0.44
     roles
    0.44
     weed
    0.43
     purview
    0.43
     erroneously
    0.41
     c
    0.41
    levard
    0.41
    equity
    0.39
     wą
    0.39
     ö
    0.39
    POSITIVE LOGITS
     Maschine
    0.61
    畨
    0.55
    他說
    0.52
     Trabalho
    0.52
     Schwester
    0.52
     schöne
    0.51
    ➋
    0.50
    燔
    0.50
    傌
    0.50
     Instinct
    0.49
    Activations Density 0.000%

    No Known Activations