© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209716
    Prev
    Next
    INDEX
    Explanations

    specifically sustained-release

    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_10_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
    ك
    0.61
    ת
    0.53
    شك
    0.52
     ribosomes
    0.52
     entidad
    0.51
     Utilizamos
    0.50
    И
    0.49
     cromosoma
    0.49
    М
    0.48
     ocupa
    0.47
    POSITIVE LOGITS
    Name
    0.59
    jährigen
    0.49
    rene
    0.48
     уены
    0.47
    estellten
    0.46
    ciate
    0.46
    Signs
    0.45
    arians
    0.44
     Chronicle
    0.44
    ciata
    0.44
    Activations Density 0.000%

    No Known Activations