© 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. 38616
    Prev
    Next
    INDEX
    Explanations

    nuclear energy, party

    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
    is
    0.70
    re
    0.65
    h
    0.63
    hled
    0.62
    i
    0.62
    voll
    0.61
    Hand
    0.59
    hot
    0.59
    ud
    0.58
    den
    0.58
    POSITIVE LOGITS
    க்கு
    0.72
    一
    0.71
    고
    0.71
    א
    0.67
    اة
    0.65
    不太
    0.64
    و
    0.64
    да
    0.62
    기
    0.60
    ৩
    0.59
    Activations Density 0.020%

    No Known Activations