© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 134071
    Prev
    Next
    INDEX
    Explanations

    math operations

    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
     Sunderland
    0.42
     Ranbir
    0.41
     man
    0.40
     Sank
    0.39
    粉
    0.38
     lb
    0.37
    χο
    0.37
    ْنَ
    0.37
     powder
    0.36
     Dans
    0.36
    POSITIVE LOGITS
     бу
    0.46
     kube
    0.42
    BU
    0.41
    থে
    0.41
    PU
    0.40
     PUC
    0.40
     বু
    0.39
    Separate
    0.39
    olds
    0.38
     پیچھے
    0.38
    Activations Density 0.001%

    No Known Activations