© 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. 61449
    Prev
    Next
    INDEX
    Explanations

    months

    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
     Two
    0.50
    X
    0.49
     Six
    0.46
     X
    0.45
    x
    0.44
    χ
    0.44
    lt
    0.42
    ll
    0.42
    Two
    0.41
    lty
    0.41
    POSITIVE LOGITS
     Renderer
    0.40
    Eve
    0.39
    Cemento
    0.39
    WithString
    0.38
     Patten
    0.37
    Join
    0.37
     사항
    0.36
    Patricia
    0.36
     sağ
    0.36
    Schemas
    0.36
    Activations Density 0.002%

    No Known Activations