© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 178664
    Prev
    Next
    INDEX
    Explanations

    docker-compose yaml versions

    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_24_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
    et
    0.44
    on
    0.42
    r
    0.42
    because
    0.42
    journey
    0.40
    contin
    0.39
     descanso
    0.39
    porque
    0.39
     gearbox
    0.39
     koska
    0.38
    POSITIVE LOGITS
    荽
    0.49
    放題
    0.45
    正式
    0.45
    UISelectors
    0.45
     ازيكم
    0.43
     памят
    0.42
     fonbet
    0.41
    ड़ियों
    0.41
     Faculty
    0.39
     మై
    0.39
    Activations Density 0.000%

    No Known Activations