© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213493
    Prev
    Next
    INDEX
    Explanations

    APS

    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_47_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
    浃
    0.40
    Mp
    0.38
    Tue
    0.38
    Maur
    0.38
    Cao
    0.37
    apuris
    0.37
    acteur
    0.37
     factorización
    0.37
    Knife
    0.36
    ါ
    0.36
    POSITIVE LOGITS
    িয়া
    0.41
    ulia
    0.39
    ليا
    0.39
    soft
    0.39
    julia
    0.39
    ba
    0.39
     Bailey
    0.37
    uba
    0.37
    ilia
    0.36
     gentle
    0.36
    Activations Density 0.000%

    No Known Activations