© 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. 235268
    Prev
    Next
    INDEX
    Explanations

    basic foundational concepts

    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
    imageList
    0.49
    DBOutput
    0.40
    ysł
    0.39
    餾
    0.38
     చెప్ప
    0.38
    inputSet
    0.38
    ασία
    0.38
     ponerse
    0.37
    ://$
    0.37
     пов
    0.36
    POSITIVE LOGITS
     기초
    0.41
     Swallow
    0.40
     K
    0.39
     بنیادی
    0.39
    Basic
    0.39
     Gun
    0.38
    basic
    0.38
     گویا
    0.38
    Base
    0.37
    broad
    0.37
    Activations Density 0.007%

    No Known Activations