© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 152327
    Prev
    Next
    INDEX
    Explanations

    Fibonacci sequence

    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
    ید
    0.54
     ی
    0.50
    $/
    0.44
     daje
    0.44
     yeni
    0.44
    تی
    0.44
    ∈</
    0.44
    Encoding
    0.43
     为
    0.42
     to
    0.42
    POSITIVE LOGITS
    olla
    0.45
    rale
    0.45
     Sick
    0.44
    stone
    0.43
    rawl
    0.42
    olate
    0.41
    culture
    0.41
    oplane
    0.41
    stern
    0.40
    rao
    0.40
    Activations Density 0.000%

    No Known Activations