© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50644
    Prev
    Next
    INDEX
    Explanations

    color or monochrome images/displays

    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_10_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
    ’
    0.65
     e
    0.59
     an
    0.56
    '
    0.55
     {
    0.55
    ED
    0.54
     expiration
    0.54
     impairment
    0.53
    2
    0.53
     et
    0.53
    POSITIVE LOGITS
    ુ
    0.63
     Wissenschaft
    0.63
    Neha
    0.62
     ውሃ
    0.61
    يلة
    0.60
    rijke
    0.60
    نيه
    0.59
    bares
    0.59
     Leser
    0.58
    يله
    0.58
    Activations Density 0.019%

    No Known Activations