© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144219
    Prev
    Next
    INDEX
    Explanations

    consonant, consecutive, condensed, consul, command

    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_0_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
    r
    1.94
    ۹
    1.91
    7
    1.88
    t
    1.82
    9
    1.68
    l
    1.66
    i
    1.61
    ne
    1.59
    with
    1.59
    w
    1.55
    POSITIVE LOGITS
    س
    1.82
     are
    1.55
    ا
    1.52
    า
    1.45
    к
    1.38
    ور
    1.31
    ג
    1.29
     as
    1.27
    с
    1.22
    ας
    1.19
    Activations Density 0.042%

    No Known Activations