© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207299
    Prev
    Next
    INDEX
    Explanations

    understand you

    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_20_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
    infos
    0.39
    çok
    0.39
    czna
    0.38
    fic
    0.38
    cin
    0.37
    fait
    0.37
    cznie
    0.36
    ú
    0.36
    se
    0.36
    ச்செய
    0.36
    POSITIVE LOGITS
    ブレー
    0.42
     falla
    0.38
    汇
    0.37
     ባህ
    0.36
     возле
    0.35
     illust
    0.34
     машиналары
    0.34
     граждан
    0.34
     проводить
    0.33
     земле
    0.33
    Activations Density 0.002%

    No Known Activations