© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193271
    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_4_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
    ↵↵
    0.48
    nemen
    0.47
    noy
    0.47
    lesen
    0.47
    használ
    0.46
    malign
    0.46
    nina
    0.46
     వచ్చిన
    0.44
    asey
    0.44
     ጊዜ
    0.43
    POSITIVE LOGITS
     cards
    0.62
    
    0.55
     transformers
    0.54
     Cards
    0.50
     cardinals
    0.49
    ⟣
    0.48
     ceramic
    0.47
     piedi
    0.47
     circuit
    0.47
    osphere
    0.47
    Activations Density 0.000%

    No Known Activations