© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79647
    Prev
    Next
    INDEX
    Explanations

    ubiquitous

    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
    с
    1.48
    ру
    1.28
    ρα
    1.18
    s
    1.13
    स
    1.09
    س
    1.04
    the
    1.02
    ți
    1.01
    ુ
    1.00
    ład
    0.99
    POSITIVE LOGITS
    ل
    1.40
    ното
    1.38
     diarias
    1.36
    IS
    1.34
    ↵↵
    1.31
    ת
    1.31
    nake
    1.29
    nél
    1.26
    nies
    1.23
     específicas
    1.23
    Activations Density 0.001%

    No Known Activations