© 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. 99135
    Prev
    Next
    INDEX
    Explanations

    mango, acetone, cheetah, breast, veins, unsaturated

    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
     Узбеки
    0.16
    Acet
    0.16
     Acet
    0.15
     sytu
    0.15
    痠
    0.15
     Mitochond
    0.14
     букмекерская
    0.14
     możesz
    0.14
     Fonbet
    0.14
     mogą
    0.14
    POSITIVE LOGITS
    ્યા
    0.13
     vele
    0.13
    自我
    0.12
    この
    0.12
    した
    0.12
    Ｍ
    0.12
     clings
    0.12
    亢
    0.11
    स्व
    0.11
     postponed
    0.11
    Activations Density 0.016%

    No Known Activations