© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27915
    Prev
    Next
    INDEX
    Explanations

    formulas for calculations

    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_40_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
    ',{
    0.37
     estimators
    0.36
    normal
    0.36
     Goldsmith
    0.35
    গ্রাফ
    0.35
    Axes
    0.34
    say
    0.34
    Estim
    0.33
    inschaft
    0.33
     say
    0.32
    POSITIVE LOGITS
     sputtering
    0.37
    ساب
    0.37
     barrier
    0.34
     microwave
    0.34
     pH
    0.33
    仅
    0.33
     과학
    0.33
    pH
    0.32
     explosive
    0.32
    ensão
    0.32
    Activations Density 0.022%

    No Known Activations