© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41109
    Prev
    Next
    INDEX
    Explanations

    riboside, effect, fish, cables, binding, foot

    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_3_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
    含ま
    0.63
     Origami
    0.62
    ƴ
    0.61
    ORM
    0.61
    い
    0.60
    ӧ
    0.60
     cushioning
    0.59
    는데요
    0.59
     Aquatic
    0.59
     repellent
    0.59
    POSITIVE LOGITS
    n
    1.19
    al
    0.89
    س
    0.81
    大
    0.80
    enar
    0.78
    to
    0.74
    en
    0.73
    s
    0.72
    话
    0.72
    емые
    0.71
    Activations Density 0.006%

    No Known Activations