© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200905
    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_6_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
     on
    1.20
    р
    1.04
    (
    1.03
    ering
    1.01
    る
    1.01
    \
    0.97
    ances
    0.92
     clinical
    0.91
    jectories
    0.91
     and
    0.90
    POSITIVE LOGITS
    Ｉ
    1.10
     auxilia
    1.02
     dvara
    1.02
     erweit
    1.01
    زين
    0.99
     forgo
    0.96
    Ｈ
    0.89
    Ｏ
    0.89
     gacche
    0.87
     tý
    0.87
    Activations Density 0.000%

    No Known Activations