© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142656
    Prev
    Next
    INDEX
    Explanations

    Maison Rose, Maison Carrée, cuisine

    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_0_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
    то
    1.55
     hapl
    1.38
     arbres
    1.37
    ש
    1.37
     ilang
    1.35
     cambia
    1.34
    ת
    1.30
    ໃຫ້
    1.30
     ако
    1.30
     ficar
    1.27
    POSITIVE LOGITS
    I
    1.69
    AL
    1.56
    ON
    1.42
    IO
    1.42
    Y
    1.41
     in
    1.41
    lar
    1.38
    AT
    1.37
    EY
    1.35
    It
    1.34
    Activations Density 0.000%

    No Known Activations