© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35468
    Prev
    Next
    INDEX
    Explanations

    going to

    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_11_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
    ads
    0.68
    ม
    0.67
    usr
    0.63
    ad
    0.63
    -
    0.60
     Pobl
    0.59
    ha
    0.58
    ta
    0.57
    assel
    0.57
    pesar
    0.56
    POSITIVE LOGITS
     to
    0.68
     emphas
    0.62
     توقع
    0.61
     будет
    0.59
    𝙇
    0.57
     louder
    0.57
     morbidity
    0.57
     nécess
    0.56
     тариф
    0.56
     stressing
    0.56
    Activations Density 0.001%

    No Known Activations