© 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. 112783
    Prev
    Next
    INDEX
    Explanations

    line segments and boundaries

    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
    ري
    1.54
    يد
    1.30
     as
    1.29
    ב
    1.20
    da
    1.17
    2
    1.13
    не
    1.12
    يه
    1.12
    .
    1.10
    j
    1.05
    POSITIVE LOGITS
    Line
    1.35
     خط
    1.17
     Line
    1.16
    ان
    1.13
    線の
    1.13
     линии
    1.13
     line
    1.09
    Linea
    1.09
    ους
    1.08
    Lines
    1.07
    Activations Density 0.013%

    No Known Activations