© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 211500
    Prev
    Next
    INDEX
    Explanations

    programming code

    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_43_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
    布局
    0.49
    atthena
    0.46
     UIImageView
    0.46
    anav
    0.46
     музыку
    0.44
     BSData
    0.43
    <unused92>
    0.43
    MovieModal
    0.43
     музыки
    0.43
     अंडे
    0.42
    POSITIVE LOGITS
     co
    0.38
    err
    0.37
     Amateur
    0.36
     Gent
    0.36
     ठर
    0.35
     assigned
    0.35
     ل
    0.34
     viene
    0.34
     Logical
    0.34
     zad
    0.34
    Activations Density 0.001%

    No Known Activations