© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138761
    Prev
    Next
    INDEX
    Explanations

    foreign language snippets

    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
     Cull
    0.45
    itchfield
    0.41
     Baldwin
    0.40
     share
    0.40
     sly
    0.40
    ーク
    0.39
     Share
    0.39
    既
    0.39
     balancing
    0.38
    鼎
    0.38
    POSITIVE LOGITS
    வாய
    0.44
    ников
    0.37
    initConfig
    0.35
    ioribus
    0.35
     mendatang
    0.35
     induk
    0.34
    inplace
    0.33
     হানি
    0.33
    𝑓
    0.33
     descends
    0.33
    Activations Density 0.014%

    No Known Activations