© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175049
    Prev
    Next
    INDEX
    Explanations

    describe capabilities

    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
     sempre
    0.44
    ➌
    0.42
    orkel
    0.42
     config
    0.41
     всегда
    0.41
     all
    0.40
     ancora
    0.40
     Philadelphia
    0.39
     always
    0.39
     mindig
    0.39
    POSITIVE LOGITS
     niektórych
    0.47
     někter
    0.46
     치료
    0.45
    ându
    0.45
     základě
    0.45
     죽
    0.44
     mencegah
    0.43
     dacă
    0.43
    kách
    0.43
     기술
    0.42
    Activations Density 0.002%

    No Known Activations