© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 150244
    Prev
    Next
    INDEX
    Explanations

    code and data structures

    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_60_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
     No
    0.55
     Î
    0.52
     String
    0.50
     -
    0.48
     Fé
    0.46
     Deal
    0.45
    -"+
    0.44
     Do
    0.43
     Š
    0.43
     Â
    0.43
    POSITIVE LOGITS
    цы
    0.44
     that
    0.42
    I
    0.41
    дей
    0.40
    that
    0.38
    That
    0.38
    вайте
    0.38
     chaotic
    0.37
    JsonKey
    0.37
    0
    0.37
    Activations Density 0.002%

    No Known Activations