© 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. 208552
    Prev
    Next
    INDEX
    Explanations

    "Monnieri", "Rosea", "Terrestris", "iatica"

    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
     桌
    0.22
     tavolo
    0.20
     deceduto
    0.20
    ảng
    0.20
     aproximativ
    0.20
     використову
    0.20
     descobrir
    0.20
     áo
    0.19
     escolher
    0.19
     angolo
    0.19
    POSITIVE LOGITS
    zeta
    0.20
    w
    0.20
    wit
    0.19
    unen
    0.19
    None
    0.18
    reliability
    0.18
    ppb
    0.18
    n
    0.18
     الده
    0.17
    alc
    0.17
    Activations Density 0.001%

    No Known Activations