© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103878
    Prev
    Next
    INDEX
    Explanations

    ach followed by "an", "ian", "Road", "DB", "Stre", "motivating"

    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_1_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
    in
    0.91
    玼
    0.79
    萻
    0.75
     the
    0.74
    <0x0D>
    0.74
     relive
    0.73
    :
    0.71
    㡀
    0.70
    此
    0.70
    𝙊
    0.70
    POSITIVE LOGITS
    ли
    1.36
    3
    1.30
    ec
    1.21
    4
    1.17
    ed
    1.13
    ol
    1.11
    í
    1.11
    .,
    1.09
    ra
    1.09
    la
    1.07
    Activations Density 0.000%

    No Known Activations