© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40750
    Prev
    Next
    INDEX
    Explanations

    go through

    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_11_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
    Bots
    0.45
     \
    0.40
    Sit
    0.38
    Waves
    0.38
    D
    0.38
    ,\
    0.37
    Cal
    0.37
    Ral
    0.37
    Tel
    0.36
    F
    0.36
    POSITIVE LOGITS
     zadovol
    0.40
    𝐫
    0.40
     skateboard
    0.39
     perut
    0.39
    ла
    0.38
     soddis
    0.38
    ↵↵
    0.38
     šport
    0.38
     креди
    0.37
     spelen
    0.37
    Activations Density 0.002%

    No Known Activations