© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 112020
    Prev
    Next
    INDEX
    Explanations

    alloc, scenario, context

    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_2_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
     be
    1.56
    T
    1.48
     it
    1.22
    ere
    1.13
    W
    1.09
     I
    1.08
    高
    1.06
    ال
    1.03
     It
    1.02
    V
    0.96
    POSITIVE LOGITS
    υ
    1.14
    у
    1.13
    и
    1.11
    ят
    1.10
    ﺔ
    1.09
    нг
    1.08
    க்க
    1.07
    ιν
    1.07
    х
    1.06
    مال
    1.05
    Activations Density 0.012%

    No Known Activations