© 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. 155667
    Prev
    Next
    INDEX
    Explanations

    pur

    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
     Rob
    0.38
    顼
    0.37
     ep
    0.37
     وزارت
    0.36
     важное
    0.36
    োর
    0.35
    ੌਰ
    0.34
     దు
    0.34
    vero
    0.34
     robo
    0.34
    POSITIVE LOGITS
    med
    0.46
    Med
    0.42
    ggbb
    0.42
    鍚
    0.42
    مح
    0.41
     med
    0.41
     Barr
    0.41
    Lil
    0.39
     Med
    0.39
    Litt
    0.39
    Activations Density 0.001%

    No Known Activations