© 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. 39635
    Prev
    Next
    INDEX
    Explanations

    corticosteroids

    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
    c
    0.84
    ל
    0.73
    лната
    0.68
    gawa
    0.65
    ﺑ
    0.64
    bley
    0.63
     nhàng
    0.63
    ﺙ
    0.62
    cery
    0.61
    
    0.61
    POSITIVE LOGITS
    2
    0.86
    0
    0.68
    िक
    0.66
    اب
    0.64
    ش
    0.64
    та
    0.62
     kot
    0.61
    ни
    0.60
    IR
    0.59
     for
    0.58
    Activations Density 0.004%

    No Known Activations