© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116694
    Prev
    Next
    INDEX
    Explanations

    wall-mounted

    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_27_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
    が入
    0.38
     ruf
    0.37
    ர்ம
    0.36
     先
    0.36
    伪
    0.36
     пере
    0.36
     sous
    0.36
     cdot
    0.36
    нтип
    0.35
    كتوبر
    0.35
    POSITIVE LOGITS
    lattice
    0.35
    zięki
    0.35
    फिल
    0.34
    Bez
    0.33
    Wiring
    0.32
    Observation
    0.31
     চিকিৎ
    0.30
    ինչ
    0.30
    靑
    0.30
     گا۔
    0.30
    Activations Density 0.002%

    No Known Activations