© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 150958
    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_59_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
     f
    3.63
     ف
    2.72
    f
    2.03
     फ
    1.87
    ｆ
    1.59
    ฟ
    1.52
     ф
    1.37
     ฟ
    1.31
     ফ
    1.27
    𝑓
    1.16
    POSITIVE LOGITS
    FRANK
    0.37
    Fre
    0.35
    費
    0.35
     FAC
    0.34
    แฟ
    0.34
    フラ
    0.34
    唏
    0.34
     وفر
    0.34
    FIL
    0.33
     φι
    0.33
    Activations Density 0.003%

    No Known Activations