© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106349
    Prev
    Next
    INDEX
    Explanations

    technical code snippets

    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_1_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
    I
    1.12
    U
    1.06
    T
    1.00
    在
    0.99
     ຄ
    0.98
    R
    0.98
    S
    0.98
    K
    0.98
    𝙸
    0.96
    Y
    0.96
    POSITIVE LOGITS
    at
    1.32
    with
    1.32
    ية
    1.16
    ul
    1.15
    as
    1.09
    were
    1.07
    p
    1.07
    of
    1.04
    0
    1.02
    า
    1.02
    Activations Density 0.006%

    No Known Activations