© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56706
    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_11_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
     berl
    0.50
     terce
    0.49
     culturales
    0.49
     jednym
    0.49
    코드
    0.47
     센
    0.46
     크게
    0.46
    ၁
    0.44
     மூன்ற
    0.44
     מת
    0.44
    POSITIVE LOGITS
     addresses
    0.46
    addresses
    0.44
    ETERS
    0.44
    http
    0.43
    nn
    0.42
     GREEN
    0.42
     addressed
    0.42
    composed
    0.42
    ä
    0.42
     EDIT
    0.42
    Activations Density 0.000%

    No Known Activations