© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 60001
    Prev
    Next
    INDEX
    Explanations

    commas

    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_59_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
     U
    0.41
    RC
    0.40
    Diag
    0.38
     K
    0.38
    perg
    0.38
    lng
    0.38
     Jn
    0.37
    ڪ
    0.37
     ln
    0.36
     Ln
    0.36
    POSITIVE LOGITS
    City
    0.50
     City
    0.46
    State
    0.46
     المدينة
    0.45
    岡山
    0.45
    Leeds
    0.43
     수원
    0.42
     Salford
    0.42
    CITY
    0.42
    Ciudad
    0.42
    Activations Density 0.000%

    No Known Activations