© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 197179
    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_9_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
    K
    0.54
    V
    0.49
    AY
    0.47
    plify
    0.47
    kelly
    0.46
    "
    0.45
    R
    0.45
    x
    0.45
     Kelly
    0.45
    C
    0.43
    POSITIVE LOGITS
     призна
    0.54
    <unused693>
    0.53
     бра
    0.52
    琕
    0.52
     程序
    0.51
     φυ
    0.51
     ଗ
    0.51
    莪
    0.51
     ግራም
    0.50
     ἐ
    0.50
    Activations Density 0.000%

    No Known Activations