© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32730
    Prev
    Next
    INDEX
    Explanations

    hold

    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
     이용
    0.42
     genital
    0.41
    펼
    0.40
    čení
    0.39
     Fou
    0.38
    úsc
    0.38
     이용해서
    0.38
    袒
    0.37
    IsEnabled
    0.37
     ঘন্
    0.37
    POSITIVE LOGITS
     держа
    0.50
     hold
    0.46
     Hold
    0.46
    持有
    0.44
    Holding
    0.44
     holding
    0.44
    แล้ว
    0.44
    HOLD
    0.43
    holding
    0.43
     HOLD
    0.43
    Activations Density 0.001%

    No Known Activations