© 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. 127645
    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_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
    ৮
    0.79
    ৭
    0.75
    то
    0.73
     in
    0.70
     tür
    0.70
     merav
    0.68
    ৯
    0.67
    ৬
    0.67
     bulunduğu
    0.66
    ৩
    0.66
    POSITIVE LOGITS
    the
    0.73
    P
    0.64
    G
    0.63
    bes
    0.58
    은
    0.57
    E
    0.57
    C
    0.56
    D
    0.56
    have
    0.55
    ခဲ့
    0.55
    Activations Density 0.000%

    No Known Activations