© 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. 236786
    Prev
    Next
    INDEX
    Explanations

    fats

    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
    아가
    0.45
     réduit
    0.43
    reduce
    0.42
    减少
    0.41
    減少
    0.39
    ícia
    0.39
    Reduce
    0.39
     돌
    0.39
     reduce
    0.38
    abbr
    0.38
    POSITIVE LOGITS
     WF
    0.42
     මැ
    0.39
    দানের
    0.38
    fänger
    0.37
    itelist
    0.37
    恫
    0.37
     wf
    0.36
    ElementsBy
    0.35
     WI
    0.35
     Connie
    0.35
    Activations Density 0.004%

    No Known Activations