© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53746
    Prev
    Next
    INDEX
    Explanations

    quirky

    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_55_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
    y
    0.52
    ies
    0.48
    ys
    0.39
     отклю
    0.39
     gameOver
    0.39
    IES
    0.38
    yte
    0.38
     remplacement
    0.38
     замени
    0.38
    ｙ
    0.37
    POSITIVE LOGITS
    瞇
    0.43
    క్కి
    0.42
    SHORT
    0.42
    ઓની
    0.40
    Be
    0.39
    悧
    0.39
    黢
    0.39
    गत
    0.39
    Kali
    0.38
    短
    0.38
    Activations Density 0.001%

    No Known Activations