© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12644
    Prev
    Next
    INDEX
    Explanations

    sides of equations

    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_13_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
    jo
    0.65
    j
    0.59
    eto
    0.55
    fox
    0.54
    ver
    0.54
    oso
    0.50
     ទ
    0.49
    man
    0.49
    ır
    0.49
    ጮ
    0.49
    POSITIVE LOGITS
    ی
    0.58
    イナー
    0.48
    낫
    0.48
     balances
    0.47
    ालय
    0.47
    羙
    0.47
    াউন
    0.46
    Alchemy
    0.46
     Fondation
    0.46
    ინი
    0.46
    Activations Density 0.063%

    No Known Activations