© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5678
    Prev
    Next
    INDEX
    Explanations

    f

    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_44_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
    уре
    0.37
    ovina
    0.37
    㞰
    0.37
    آپ
    0.36
    traumatic
    0.36
    ペア
    0.36
     Bagley
    0.36
     Alcoholic
    0.35
    ymi
    0.35
    濫
    0.35
    POSITIVE LOGITS
    requent
    0.60
     फ
    0.59
     Fahrenheit
    0.57
     fars
    0.54
    ຟ
    0.54
    uchsia
    0.54
    fundamentals
    0.53
    f
    0.53
     f
    0.52
    Firing
    0.52
    Activations Density 0.188%

    No Known Activations