© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 153442
    Prev
    Next
    INDEX
    Explanations

    www

    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_60_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
    .
    0.72
    [
    0.60
     reader
    0.46
     He
    0.42
    .”
    0.41
     Reader
    0.40
    ]
    0.39
    ”
    0.39
     lie
    0.39
    ).
    0.38
    POSITIVE LOGITS
    Board
    0.62
    板
    0.50
    Kaynakça
    0.46
    rzed
    0.45
    pèce
    0.44
    値下げ
    0.43
    ționale
    0.43
    बोर्ड
    0.42
    取締役
    0.42
     बोर्ड
    0.42
    Activations Density 0.000%

    No Known Activations