© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 216091
    Prev
    Next
    INDEX
    Explanations

    man

    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_47_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
    uelo
    0.35
    ∟
    0.35
     ยาก
    0.35
    hältnis
    0.34
    烨
    0.34
    kelig
    0.34
    羔
    0.33
    Ⲇ
    0.33
    চে
    0.33
    ದಲ
    0.33
    POSITIVE LOGITS
     man
    2.61
     Man
    2.11
    Man
    2.02
    man
    1.77
    マン
    1.71
     MAN
    1.66
     manned
    1.63
     ман
    1.53
     مان
    1.51
     manpower
    1.48
    Activations Density 0.001%

    No Known Activations