© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 217425
    Prev
    Next
    INDEX
    Explanations

    Format / structure

    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_16_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
     sagte
    0.50
    ᕝ
    0.50
     गई
    0.47
     તેણીએ
    0.43
     zei
    0.43
     карта
    0.42
     davran
    0.42
     خداوند
    0.42
    蜈
    0.42
     лет
    0.42
    POSITIVE LOGITS
    location
    0.57
    ⁄
    0.48
     九
    0.47
    LOCATION
    0.45
    cipher
    0.45
    removeAttribute
    0.44
     chín
    0.44
     أنا
    0.43
    zipped
    0.43
     DeConcini
    0.43
    Activations Density 0.000%

    No Known Activations