© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134459
    Prev
    Next
    INDEX
    Explanations

    Write documentation or code

    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_37_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
     smoking
    0.42
    wann
    0.39
     Guys
    0.38
    сем
    0.37
     Smoking
    0.37
    orgement
    0.37
    issuer
    0.37
    喫
    0.37
    igungen
    0.35
    smoking
    0.35
    POSITIVE LOGITS
    يدا
    0.39
     архитек
    0.38
    Colonne
    0.38
    正则表达式
    0.38
     journalism
    0.38
     decorating
    0.38
     screenplay
    0.38
     Psal
    0.37
    WordPress
    0.37
     طراحی
    0.37
    Activations Density 0.120%

    No Known Activations