© 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. 68218
    Prev
    Next
    INDEX
    Explanations

    C++ programming

    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
     F
    0.53
     vanilla
    0.48
     Vanilla
    0.45
    ধ্যার
    0.45
     van
    0.44
    環境
    0.44
    van
    0.43
    Van
    0.42
    Vanilla
    0.42
    F
    0.42
    POSITIVE LOGITS
     Compact
    0.40
     sulf
    0.38
     solute
    0.38
    ostino
    0.38
     Solomon
    0.38
     Component
    0.37
    는지
    0.37
     ニ
    0.37
     sus
    0.36
     Cd
    0.36
    Activations Density 0.008%

    No Known Activations