© 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. 157907
    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
    та
    1.22
    大
    1.16
    .
    1.12
     axles
    1.09
    이지만
    1.05
     fillets
    1.04
     tassels
    0.99
     pulleys
    0.98
     effluents
    0.96
     editorials
    0.95
    POSITIVE LOGITS
     it
    1.18
    text
    1.02
    )
    0.94
    that
    0.87
    er
    0.86
    mathbf
    0.86
     don
    0.86
    state
    0.82
     that
    0.78
     You
    0.78
    Activations Density 0.000%

    No Known Activations