© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68864
    Prev
    Next
    INDEX
    Explanations

    Dead

    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_46_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
     dead
    1.15
    Dead
    1.11
    dead
    1.10
     Dead
    1.07
    死
    1.02
     DEAD
    0.98
    DEAD
    0.93
     死
    0.82
     मृत
    0.80
     মৃত
    0.79
    POSITIVE LOGITS
     identification
    0.39
     mass
    0.37
     rising
    0.36
     Dior
    0.35
     raise
    0.34
     نہ
    0.34
    writeHead
    0.34
    volta
    0.34
     dior
    0.34
     rise
    0.34
    Activations Density 0.001%

    No Known Activations