© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138648
    Prev
    Next
    INDEX
    Explanations

    map coordinates

    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_37_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
     Korn
    0.39
     Cooley
    0.38
    Struct
    0.37
    Diet
    0.36
    Besch
    0.36
     getDescription
    0.36
     システム
    0.35
    Ｄ
    0.35
     Hardy
    0.35
    Ij
    0.35
    POSITIVE LOGITS
     नका
    0.46
     geospatial
    0.44
     mapView
    0.43
    Map
    0.41
     mapas
    0.41
     Map
    0.40
    MapView
    0.40
    地理
    0.39
     geographic
    0.39
     fadeInUp
    0.39
    Activations Density 0.000%

    No Known Activations