© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209118
    Prev
    Next
    INDEX
    Explanations

    over

    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
     means
    0.45
    ภายใน
    0.45
    Coming
    0.44
    ܤ
    0.43
     Coming
    0.43
     binnen
    0.43
    Means
    0.41
    means
    0.40
    му
    0.40
    ну
    0.39
    POSITIVE LOGITS
    ustering
    0.50
    ricamente
    0.46
    erical
    0.43
     escolh
    0.43
     தெரி
    0.42
     protagonist
    0.42
     номера
    0.42
    .°
    0.42
     ташки
    0.42
     लटका
    0.42
    Activations Density 0.001%

    No Known Activations