© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173994
    Prev
    Next
    INDEX
    Explanations

    after inclusion or addition

    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_20_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
    。"
    0.47
    蝣
    0.46
     छूट
    0.45
    追い
    0.45
    ቹን
    0.44
     цього
    0.43
    این
    0.43
     খুঁজতে
    0.43
     այդ
    0.43
    🛳
    0.42
    POSITIVE LOGITS
    ovat
    0.48
    ,\,\
    0.42
     house
    0.42
    ocentric
    0.41
     eV
    0.40
    面包
    0.40
     place
    0.40
     fiery
    0.40
     sim
    0.39
     socio
    0.39
    Activations Density 0.002%

    No Known Activations