© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 78698
    Prev
    Next
    INDEX
    Explanations

    email subject lines

    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_29_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
    ovec
    0.38
    ոլ
    0.38
    砷
    0.37
     ойно
    0.36
    मती
    0.36
    ssch
    0.35
    CEED
    0.35
    άλ
    0.35
    شوف
    0.35
    地域の
    0.35
    POSITIVE LOGITS
     detractors
    0.48
     convection
    0.39
     Equation
    0.37
     displeasure
    0.35
    prediction
    0.35
     அல்ல
    0.34
     মোঃ
    0.34
    ᆨ
    0.34
    مكن
    0.33
     Reclamation
    0.33
    Activations Density 0.003%

    No Known Activations