© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89974
    Prev
    Next
    INDEX
    Explanations

    vibrant, consistent, waste, bord, ingen, vibrante

    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_11_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
    䍧
    0.53
    there
    0.52
    पीसी
    0.52
    ijing
    0.52
    ittu
    0.50
    迫
    0.50
    was
    0.49
    ibi
    0.49
    이었
    0.49
    스로
    0.49
    POSITIVE LOGITS
    ın
    0.64
     inov
    0.64
     constantemente
    0.61
     Alliance
    0.61
     Netzwerk
    0.59
    Alliance
    0.57
     iStock
    0.57
    ;
    0.57
     সবসময়
    0.56
    <0x0D>
    0.55
    Activations Density 0.018%

    No Known Activations