© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 224413
    Prev
    Next
    INDEX
    Explanations

    graphviz visualization code

    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
     It
    0.65
     If
    0.53
     James
    0.53
    0.53
     We
    0.52
     m
    0.48
     John
    0.47
     United
    0.47
     US
    0.47
     Since
    0.47
    POSITIVE LOGITS
    eosin
    0.60
    지
    0.58
     REGIUNI
    0.56
    ≒
    0.55
     olympiques
    0.55
    peliculas
    0.55
     humaines
    0.54
    ifikasi
    0.54
     algéb
    0.53
     molécules
    0.53
    Activations Density 0.000%

    No Known Activations