© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 2837
    Prev
    Next
    INDEX
    Explanations

    too much

    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_44_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
     ასევე
    0.44
     এটাও
    0.38
    kosť
    0.37
    coran
    0.36
    :/
    0.35
    య్య
    0.33
     nedir
    0.33
    UOUS
    0.33
    ocument
    0.33
     Liquid
    0.33
    POSITIVE LOGITS
     too
    1.90
    too
    1.65
    Too
    1.34
     TOO
    1.25
     Too
    1.24
    太
    1.10
    TOO
    1.05
     слишком
    1.04
     troppo
    0.93
     demasiado
    0.91
    Activations Density 0.272%

    No Known Activations