© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82044
    Prev
    Next
    INDEX
    Explanations

    i

    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_53_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
     Lith
    0.43
    ши
    0.40
    yi
    0.40
    lith
    0.40
    ㅛ
    0.40
     शी
    0.40
    ZI
    0.39
    isian
    0.39
     RD
    0.39
    stel
    0.38
    POSITIVE LOGITS
     roz
    0.43
    Roz
    0.41
     роз
    0.40
    kosť
    0.40
     Roz
    0.40
    Ά
    0.38
    roz
    0.37
    confirmation
    0.37
    Car
    0.37
     confirmation
    0.37
    Activations Density 0.027%

    No Known Activations