© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169270
    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_56_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
     megsz
    0.36
    PTO
    0.35
    Store
    0.33
     सीख
    0.33
    digo
    0.33
    േക്ക്
    0.33
    ║
    0.33
    ɥ
    0.33
    שים
    0.32
    终
    0.32
    POSITIVE LOGITS
     holding
    3.81
    Holding
    3.39
     Holding
    3.36
    holding
    3.19
     HOLD
    1.80
     holdings
    1.63
    持
    1.52
    HOLD
    1.47
     Holdings
    1.45
    持有
    1.45
    Activations Density 0.067%

    No Known Activations