© 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. 31236
    Prev
    Next
    INDEX
    Explanations

    sky

    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
     экспеди
    0.42
    ítése
    0.39
     Rowe
    0.38
     haste
    0.38
     H
    0.38
     expedit
    0.38
    Schwe
    0.36
     Act
    0.36
    itze
    0.36
    Vars
    0.35
    POSITIVE LOGITS
     서
    0.91
    باد
    0.57
    Sky
    0.56
     Sky
    0.53
     bee
    0.51
    Sarah
    0.51
     пото
    0.50
     sky
    0.50
    抓
    0.49
    サー
    0.48
    Activations Density 0.004%

    No Known Activations