© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216962
    Prev
    Next
    INDEX
    Explanations

    will

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     cond
    0.44
    ঋ
    0.43
    Cond
    0.41
     chu
    0.40
     Likely
    0.39
     Convey
    0.38
    గల
    0.38
    cond
    0.36
     ¿
    0.36
     dense
    0.36
    POSITIVE LOGITS
     vigour
    0.40
     resol
    0.40
     Warden
    0.38
    resol
    0.38
     vigor
    0.37
    जरीवाल
    0.37
    ਼
    0.37
    пол
    0.37
     roadblock
    0.36
    ermark
    0.36
    Activations Density 0.004%

    No Known Activations