© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207550
    Prev
    Next
    INDEX
    Explanations

    bringing

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    Ấ
    0.44
     determ
    0.41
     domen
    0.40
     】,
    0.37
     liệt
    0.36
     дослі
    0.36
     Vez
    0.36
     honom
    0.35
    .],
    0.35
    揊
    0.35
    POSITIVE LOGITS
     up
    0.99
    Up
    0.80
    up
    0.79
     Up
    0.73
     lên
    0.66
    ขึ้น
    0.52
    アップ
    0.47
    起來
    0.46
    起来
    0.44
     stuff
    0.43
    Activations Density 0.001%

    No Known Activations