© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54279
    Prev
    Next
    INDEX
    Explanations

    modal windows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     blame
    0.39
     blames
    0.39
    uvat
    0.39
     siphon
    0.39
    漆
    0.38
     sillon
    0.36
     vitro
    0.36
    Trac
    0.36
     blamed
    0.35
    蝮
    0.35
    POSITIVE LOGITS
    Modal
    0.59
     modal
    0.55
     modals
    0.52
     Modal
    0.50
    modal
    0.47
    MovieModal
    0.42
     modalities
    0.39
     mens
    0.38
     সংসারের
    0.38
     provinc
    0.37
    Activations Density 0.022%

    No Known Activations