© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146087
    Prev
    Next
    INDEX
    Explanations

    y

    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
    オ
    0.39
    URIComponent
    0.37
    ო
    0.37
    🔍
    0.36
    ութ
    0.36
    επ
    0.36
    🗨
    0.36
     オ
    0.35
     leyendo
    0.35
     riding
    0.35
    POSITIVE LOGITS
    xan
    0.42
    𝑔
    0.40
    ர்களுக்கு
    0.39
    ons
    0.39
    ناد
    0.39
    nals
    0.39
    TRS
    0.38
    CSA
    0.38
     house
    0.38
    cis
    0.38
    Activations Density 0.000%

    No Known Activations