© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36932
    Prev
    Next
    INDEX
    Explanations

    Henri, Matisse, George, Bec

    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_3_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
    aría
    0.73
    的
    0.59
    ρί
    0.56
     धोनी
    0.55
     membres
    0.54
    itado
    0.53
    istro
    0.53
    🎰
    0.52
    incar
    0.52
     سک
    0.52
    POSITIVE LOGITS
    ה
    0.76
    a
    0.63
    c
    0.63
     OM
    0.62
    ኀ
    0.60
     Sway
    0.60
     Insgesamt
    0.59
     DR
    0.59
     OMX
    0.58
     ISP
    0.58
    Activations Density 0.000%

    No Known Activations