© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 100968
    Prev
    Next
    INDEX
    Explanations

    digits or words ending in

    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_16_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
    ጩ
    0.48
     negotiate
    0.47
     contribute
    0.47
    ሪ
    0.46
     выпа
    0.45
    <0xE3>
    0.45
     sneeze
    0.44
     mercado
    0.44
    cznej
    0.44
    ავლ
    0.44
    POSITIVE LOGITS
    ä
    0.55
    frak
    0.52
    äm
    0.52
    ekar
    0.50
    kraft
    0.48
    jawab
    0.48
    dnn
    0.47
    gia
    0.47
    д
    0.46
    baked
    0.46
    Activations Density 0.000%

    No Known Activations