© 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. 11281
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    ID
    0.48
     بينا
    0.48
    ian
    0.48
    r
    0.47
    :
    0.47
    au
    0.47
     jist
    0.46
    an
    0.45
    ella
    0.45
    nova
    0.44
    POSITIVE LOGITS
     dólares
    0.48
    Ꮁ
    0.48
    𝗬
    0.48
     exploratory
    0.47
     numArray
    0.47
    ધ્ય
    0.47
    েম
    0.46
     размер
    0.46
     allere
    0.46
     යුතුය
    0.46
    Activations Density 0.008%

    No Known Activations