© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 198537
    Prev
    Next
    INDEX
    Explanations

    springframework

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_9_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
    p
    1.16
    ra
    0.77
    c
    0.75
    اری
    0.73
     Би
    0.69
    m
    0.64
     सिंहासन
    0.64
    rane
    0.64
    houette
    0.63
     יה
    0.62
    POSITIVE LOGITS
    िंग
    0.97
    اً
    0.97
    ת
    0.93
    ב
    0.82
    其他
    0.82
     be
    0.81
    čun
    0.79
    ج
    0.79
    지
    0.79
    اع
    0.78
    Activations Density 0.000%

    No Known Activations