© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 67551
    Prev
    Next
    INDEX
    Explanations

    H

    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_51_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
    alions
    0.42
    Fold
    0.40
    ாள
    0.39
    Sé
    0.39
    蕉
    0.38
    क्षिक
    0.38
    __'
    0.38
    AL
    0.37
    sce
    0.37
    Ava
    0.36
    POSITIVE LOGITS
     Cil
    0.40
     glue
    0.40
     Trunk
    0.39
    绿
    0.37
     gluing
    0.37
     tartoz
    0.37
     trunk
    0.36
     zelen
    0.36
    গাঁ
    0.35
     martini
    0.35
    Activations Density 0.008%

    No Known Activations