© 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
    2. Gemma-3-27B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 33950
    Prev
    Next
    INDEX
    Explanations

    Chen or Lee names

    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
    (
    0.67
    and
    0.66
    یک
    0.65
    ä
    0.63
    with
    0.62
    <0xBB>
    0.59
    )
    0.59
    écies
    0.57
     thaliana
    0.57
    **
    0.54
    POSITIVE LOGITS
    ן
    0.61
     thao
    0.57
     تعريف
    0.57
    на
    0.57
     كند
    0.56
     Alles
    0.55
    га
    0.54
     pracuje
    0.54
     schnelle
    0.53
     bordo
    0.52
    Activations Density 0.001%

    No Known Activations