© 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. 122669
    Prev
    Next
    INDEX
    Explanations

    method, way, password, seeds

    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
    á
    0.83
    ey
    0.66
    お客様
    0.66
     बिना
    0.63
    edi
    0.62
    iyordu
    0.62
    ippi
    0.62
    ine
    0.60
    ↼
    0.59
    at
    0.59
    POSITIVE LOGITS
     présent
    0.67
    ע
    0.67
    قة
    0.66
     Численность
    0.66
    ش
    0.66
     campo
    0.64
    タイ
    0.64
    ുള്ള
    0.63
     Autónoma
    0.62
    تم
    0.61
    Activations Density 0.000%

    No Known Activations