© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 66449
    Prev
    Next
    INDEX
    Explanations

    accumulations or heaps

    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
     मं
    0.43
    gnet
    0.41
    詿
    0.40
    culaire
    0.40
    鴿
    0.39
    agu
    0.38
     откуда
    0.37
     ReLU
    0.37
    :])
    0.36
    ಪ
    0.36
    POSITIVE LOGITS
     hö
    0.83
     High
    0.82
    High
    0.80
     hø
    0.75
     हाई
    0.75
     hög
    0.72
    hö
    0.71
     high
    0.70
    Hö
    0.65
     Hoch
    0.64
    Activations Density 0.004%

    No Known Activations