© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215004
    Prev
    Next
    INDEX
    Explanations

    closing code delimiters

    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
    日光
    0.42
    It
    0.39
    WebApplication
    0.37
    Weapon
    0.36
    ित
    0.35
    hilangan
    0.34
    屒
    0.34
     கலா
    0.33
    ErrorHandler
    0.33
     couverts
    0.33
    POSITIVE LOGITS
    藠
    0.40
     FHD
    0.40
    endants
    0.39
    ANDS
    0.38
     Coefficients
    0.38
    unti
    0.37
     ator
    0.37
     ECHO
    0.36
     તેમ
    0.36
    úil
    0.36
    Activations Density 0.008%

    No Known Activations