© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1828
    Prev
    Next
    INDEX
    Explanations

    figsize=(8,

    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_39_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
    ጒ
    0.40
    ሮች
    0.40
    шек
    0.39
     Seoul
    0.38
    uisce
    0.38
    Seoul
    0.38
     marchand
    0.38
    дени
    0.38
     서울
    0.37
     silice
    0.37
    POSITIVE LOGITS
     nine
    0.55
     ten
    0.50
     आठ
    0.47
     Nine
    0.47
     seven
    0.46
     九
    0.46
     девя
    0.46
     दस
    0.45
     eight
    0.45
     six
    0.44
    Activations Density 0.002%

    No Known Activations