© 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. 14699
    Prev
    Next
    INDEX
    Explanations

    nuclear or thermal energy

    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
     corros
    0.39
    ylated
    0.37
     হত্যাকা
    0.37
     BMC
    0.37
     paket
    0.37
    सदी
    0.36
     Gases
    0.36
     ஊ
    0.36
    conservation
    0.36
    નિક
    0.36
    POSITIVE LOGITS
    bag
    0.44
     термо
    0.39
     Therm
    0.38
     bag
    0.38
    Dirty
    0.38
     tide
    0.36
     therm
    0.35
     thermique
    0.35
    Therm
    0.35
    tidal
    0.34
    Activations Density 0.067%

    No Known Activations