© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27023
    Prev
    Next
    INDEX
    Explanations

    PostgreSQL operators and functions

    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_40_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
     liitty
    0.41
    summar
    0.36
     shutters
    0.35
    곤
    0.35
    وی
    0.35
     कॉनकॉर्ड
    0.35
     ವಿ
    0.34
    alg
    0.34
    谱
    0.34
    ajat
    0.34
    POSITIVE LOGITS
     कंडिशनर
    0.41
    Nash
    0.41
     schreiben
    0.40
     Nash
    0.39
     Pearce
    0.38
    蒻
    0.38
     Interactive
    0.38
     Varan
    0.38
    Interactive
    0.38
    Pear
    0.38
    Activations Density 0.008%

    No Known Activations