© 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. 176824
    Prev
    Next
    INDEX
    Explanations

    URLs and 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_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
     Heinrich
    0.44
     Farbe
    0.40
     NAR
    0.38
    stärke
    0.38
    ৩৯
    0.38
     гне
    0.37
     Fred
    0.36
    猙
    0.36
    vu
    0.36
    gebnisse
    0.36
    POSITIVE LOGITS
    Operators
    0.40
    Cyt
    0.40
    localVar
    0.39
    CompliancePolicy
    0.38
    Radi
    0.38
     cytokines
    0.38
     Rel
    0.38
     maxY
    0.37
     gra
    0.37
    лкой
    0.37
    Activations Density 0.005%

    No Known Activations