© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37415
    Prev
    Next
    INDEX
    Explanations

    still life, water, life

    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
    h
    0.89
    as
    0.82
    s
    0.80
    த்தில்
    0.76
    et
    0.75
    с
    0.74
    স
    0.74
    وم
    0.72
    az
    0.69
     {
    0.67
    POSITIVE LOGITS
    ită
    0.71
     analisis
    0.71
    ิ
    0.70
    ین
    0.68
    のために
    0.66
     materiais
    0.64
     modifica
    0.64
    िन
    0.61
    </h2>
    0.61
    एम
    0.60
    Activations Density 0.030%

    No Known Activations