© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113021
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    m
    1.30
    o
    1.30
    d
    1.30
    ln
    1.28
    ne
    1.23
    g
    1.23
    it
    1.20
    k
    1.13
    kopf
    1.07
     I
    1.05
    POSITIVE LOGITS
     powied
    1.45
    ፣
    1.29
     contribu
    1.20
     distribu
    1.20
    =>{
    1.17
    ِی
    1.16
     restitu
    1.15
     dinast
    1.15
    ித்த
    1.13
     של
    1.13
    Activations Density 0.000%

    No Known Activations