© 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. 34964
    Prev
    Next
    INDEX
    Explanations

    a comma

    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
     tamen
    0.40
    릇
    0.40
    gten
    0.38
    ının
    0.36
    ڕ
    0.35
    ąd
    0.35
    lamak
    0.35
    ”]
    0.34
    olfo
    0.33
    linson
    0.33
    POSITIVE LOGITS
     variously
    0.42
     Quote
    0.40
     quote
    0.40
     सुधा
    0.39
     say
    0.38
     alternately
    0.38
     capital
    0.37
    姚
    0.37
    quote
    0.37
     actively
    0.36
    Activations Density 0.033%

    No Known Activations