© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235296
    Prev
    Next
    INDEX
    Explanations

    names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    講師
    0.45
    𝗁
    0.41
     solving
    0.40
    ENCES
    0.39
    ęg
    0.38
    ethy
    0.38
     وفي
    0.37
    fhir
    0.37
     infer
    0.36
    𝓀
    0.36
    POSITIVE LOGITS
     Laver
    0.43
     Schilling
    0.41
     Lav
    0.38
     शेप
    0.38
    ชน
    0.36
     Stade
    0.36
    ထား
    0.36
     Shape
    0.36
     Lerner
    0.36
    विरुद्ध
    0.36
    Activations Density 0.021%

    No Known Activations