© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139395
    Prev
    Next
    INDEX
    Explanations

    breadboard or protoboard

    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_12_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
    Flare
    0.18
    Ht
    0.17
    𝙜
    0.17
    light
    0.17
    Thailand
    0.17
    Phong
    0.17
    safe
    0.17
    Forgotten
    0.17
    Thay
    0.17
    Trains
    0.17
    POSITIVE LOGITS
    ા
    0.18
    ’
    0.17
    くちゃ
    0.17
     табли
    0.17
     QTL
    0.17
     NCBI
    0.17
     frantic
    0.17
     MILLER
    0.17
     buck
    0.17
     conclusions
    0.16
    Activations Density 0.001%

    No Known Activations