© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 170614
    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_56_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
    ｐ
    0.45
     ）
    0.44
    Ύ
    0.43
    িল্প
    0.41
    𝚄
    0.40
     pcl
    0.38
    𝗽
    0.37
     」
    0.36
    nlp
    0.36
     hängt
    0.35
    POSITIVE LOGITS
    Execute
    0.38
     humanist
    0.38
    Adapter
    0.37
     TRANSFER
    0.36
    ‍♂️
    0.36
    
    0.36
    
    0.36
    
    0.36
    Encode
    0.35
    ZD
    0.35
    Activations Density 0.000%

    No Known Activations