© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48872
    Prev
    Next
    INDEX
    Explanations

    fast

    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_55_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
    indd
    0.44
     unleashed
    0.40
     centrifugation
    0.38
    osaurus
    0.38
    ifers
    0.38
    ifolia
    0.37
    टने
    0.37
    ~!
    0.37
    pgamma
    0.36
    ió
    0.36
    POSITIVE LOGITS
     fast
    0.52
     FAST
    0.49
     Fast
    0.49
     efficacement
    0.47
    Fast
    0.43
    fast
    0.43
    快
    0.43
     একবার
    0.39
     onBackPressed
    0.38
     facilmente
    0.38
    Activations Density 0.003%

    No Known Activations