© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139238
    Prev
    Next
    INDEX
    Explanations

    abstract math concepts

    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
     результата
    0.39
     correspond
    0.39
     microp
    0.39
     result
    0.38
    离
    0.38
     résultats
    0.38
     대응
    0.38
     ನೋಡ
    0.37
     বেন
    0.37
    雦
    0.37
    POSITIVE LOGITS
    frc
    0.41
    jom
    0.40
     맨
    0.40
    BC
    0.40
    W
    0.38
    νομ
    0.38
    Quantum
    0.38
    cdf
    0.37
    얄
    0.37
    elemento
    0.37
    Activations Density 0.000%

    No Known Activations