© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91453
    Prev
    Next
    INDEX
    Explanations

    OG image prompt

    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_3_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
     странице
    0.74
    ו
    0.68
     основе
    0.66
     इलाकों
    0.66
     да
    0.61
     активности
    0.61
     первый
    0.61
     упаков
    0.61
     доби
    0.59
     bạn
    0.58
    POSITIVE LOGITS
    j
    0.82
    c
    0.80
    ad
    0.76
    רי
    0.71
    د
    0.70
    ä
    0.70
    tä
    0.68
    f
    0.68
    st
    0.67
    פר
    0.67
    Activations Density 0.000%

    No Known Activations