© 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. 242609
    Prev
    Next
    INDEX
    Explanations

    power

    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
    araf
    0.43
     قدرت
    0.40
    权力
    0.39
     ძალი
    0.38
     harnessed
    0.38
    hecy
    0.38
    吨
    0.38
     power
    0.38
    商店
    0.38
    POWER
    0.37
    POSITIVE LOGITS
     ම
    0.41
    áticas
    0.40
    ivore
    0.38
     Acc
    0.37
    Acc
    0.37
     Neu
    0.37
     Gestion
    0.37
     pengelolaan
    0.36
     ACT
    0.36
    indigo
    0.36
    Activations Density 0.002%

    No Known Activations