© 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. 58229
    Prev
    Next
    INDEX
    Explanations

    say "F" words

    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
    ふ
    0.44
    玹
    0.35
    Cec
    0.35
    𒌨
    0.32
    idz
    0.32
    丘
    0.31
    ீ
    0.30
    𝒹
    0.30
    <unused92>
    0.30
    লীর
    0.30
    POSITIVE LOGITS
     Фи
    1.77
     والف
    1.70
     Фа
    1.59
     Фі
    1.56
     Ф
    1.49
    الف
    1.47
     للف
    1.45
    Фи
    1.45
     الفي
    1.45
     Фор
    1.42
    Activations Density 0.006%

    No Known Activations