© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127508
    Prev
    Next
    INDEX
    Explanations

    Powell Peralta City of Books

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    м
    0.88
    在
    0.75
    р
    0.71
     في
    0.70
    да
    0.68
    会将
    0.66
    会对
    0.65
    й
    0.65
    ش
    0.65
    ג
    0.65
    POSITIVE LOGITS
     on
    0.69
    cze
    0.68
    け
    0.67
    その
    0.66
    јединачна
    0.61
    お
    0.61
    सी
    0.60
    ocytes
    0.60
    cı
    0.60
    ים
    0.59
    Activations Density 0.000%

    No Known Activations