© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166646
    Prev
    Next
    INDEX
    Explanations

    flags and colors

    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_31_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
     meals
    0.25
     Millennium
    0.24
     బాల
    0.24
     escritório
    0.23
    Inj
    0.23
     sot
    0.22
    غم
    0.22
    籤
    0.22
     переза
    0.21
     GTI
    0.21
    POSITIVE LOGITS
    デル
    0.26
    earch
    0.25
    Centers
    0.25
     CENTERS
    0.25
     numeri
    0.25
    zoek
    0.25
    Colors
    0.25
     Designs
    0.24
     Centers
    0.24
     디자인
    0.24
    Activations Density 0.002%

    No Known Activations