© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89642
    Prev
    Next
    INDEX
    Explanations

    sieve of Eratosthenes, Art, Standard, Control, Valkyries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
     utilis
    0.14
    ဦ
    0.13
    加上
    0.13
    ብር
    0.13
    ódigo
    0.13
    ാനാ
    0.13
     sinusoid
    0.13
     iCloud
    0.13
    編曲
    0.13
    졍
    0.13
    POSITIVE LOGITS
    த்திற்காக
    0.13
    jenigen
    0.13
    D
    0.12
     গোপন
    0.12
     fraught
    0.12
     সিদ্ধান্তের
    0.12
    tableLayoutPanel
    0.12
     Und
    0.11
    ですので
    0.11
     rappro
    0.11
    Activations Density 0.015%

    No Known Activations