© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13986
    Prev
    Next
    INDEX
    Explanations

    factorize, parentheses, expand, brackets

    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
     dibangun
    0.33
    விட்டு
    0.33
     મંદ
    0.32
    conj
    0.31
     uncovered
    0.31
    джи
    0.31
    墨
    0.31
    meg
    0.31
     nella
    0.30
     isSignedIn
    0.30
    POSITIVE LOGITS
    ordering
    0.43
    ủ
    0.43
    utal
    0.41
    uar
    0.41
    ord
    0.41
    ur
    0.40
     sundry
    0.40
    otre
    0.39
    odeal
    0.39
    𝐫
    0.39
    Activations Density 0.051%

    No Known Activations