© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195794
    Prev
    Next
    INDEX
    Explanations

    donor and carrier screening

    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_15_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
    ยา
    0.28
     Belediyesi
    0.26
     магазина
    0.25
     infrastrukt
    0.25
    觞
    0.25
     coffers
    0.25
     manutenção
    0.24
     Republike
    0.24
    έ
    0.24
     arsen
    0.24
    POSITIVE LOGITS
     bevor
    0.26
     डील
    0.24
    AU
    0.24
    hann
    0.23
    incor
    0.23
    織
    0.23
    Encoding
    0.23
     mute
    0.23
     tie
    0.23
     November
    0.22
    Activations Density 0.002%

    No Known Activations