© 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. 199429
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     freezes
    0.39
     ente
    0.38
    knie
    0.38
     diz
    0.37
     RICHARD
    0.37
    ]!=
    0.37
    ardar
    0.37
     pagina
    0.37
     ارتباط
    0.36
     suced
    0.36
    POSITIVE LOGITS
    ι
    0.39
    வலி
    0.38
    Edinburgh
    0.38
    ayout
    0.38
    Nc
    0.38
    ウッド
    0.38
    wood
    0.37
    бні
    0.37
    rench
    0.37
    スメ
    0.37
    Activations Density 0.000%

    No Known Activations