© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38714
    Prev
    Next
    INDEX
    Explanations

    Group A

    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_3_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
     merciless
    0.70
     about
    0.66
    Tìm
    0.65
    ۰
    0.65
     i
    0.64
    та
    0.63
    u
    0.62
    バター
    0.61
     apne
    0.60
     навыки
    0.60
    POSITIVE LOGITS
    群
    0.63
    iritto
    0.54
    änen
    0.52
    licken
    0.49
    ੋ
    0.47
     faits
    0.47
    ोर्ट
    0.47
    Json
    0.46
    塑
    0.46
    äck
    0.46
    Activations Density 0.003%

    No Known Activations