© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150170
    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_23_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
    の
    0.54
     tratt
    0.52
     училище
    0.48
    数列
    0.48
    의
    0.48
     dí
    0.48
     वार्
    0.47
     maj
    0.47
     কি
    0.47
     キ
    0.47
    POSITIVE LOGITS
    واكب
    0.48
    erçe
    0.45
    heading
    0.44
    rein
    0.43
     scalars
    0.43
     reheating
    0.42
     capaces
    0.42
     oxidizing
    0.40
    rass
    0.40
    FRAME
    0.39
    Activations Density 0.000%

    No Known Activations