© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199537
    Prev
    Next
    INDEX
    Explanations

    such

    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_50_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
    Recommended
    0.42
     Recommended
    0.39
     Patton
    0.38
    推荐
    0.37
    Metall
    0.36
    ኤ
    0.36
     Recomend
    0.35
    metall
    0.35
    destruction
    0.35
    Wer
    0.34
    POSITIVE LOGITS
     cess
    0.45
     scaffolding
    0.45
    arti
    0.43
    呓
    0.41
    renti
    0.40
     hoist
    0.39
     winged
    0.39
     scaffolds
    0.39
     chees
    0.38
    ံ့
    0.38
    Activations Density 0.000%

    No Known Activations