© 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. 33928
    Prev
    Next
    INDEX
    Explanations

    age-old question

    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
    ES
    1.20
    ang
    1.00
    EN
    0.91
    es
    0.90
    AK
    0.89
    o
    0.86
    ED
    0.82
    ک
    0.77
    se
    0.75
    fk
    0.74
    POSITIVE LOGITS
    る
    0.63
     legt
    0.59
     έκ
    0.59
     do
    0.58
     كند
    0.58
     від
    0.57
    一提
    0.56
     دين
    0.55
     chops
    0.54
     ganglion
    0.54
    Activations Density 0.043%

    No Known Activations