© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220649
    Prev
    Next
    INDEX
    Explanations

    genes represent

    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_31_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
     தல
    0.38
    áp
    0.38
     mutil
    0.37
    越大
    0.36
     certaines
    0.35
     tamanho
    0.35
    Église
    0.35
    够
    0.35
     encaps
    0.34
    耘
    0.34
    POSITIVE LOGITS
     ഇവ
    0.40
    zels
    0.37
     $(<
    0.37
    GM
    0.37
    zeni
    0.36
    angements
    0.36
     ബി
    0.35
    受到
    0.34
     இவர்கள்
    0.33
    vieve
    0.33
    Activations Density 0.057%

    No Known Activations