© 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. 93448
    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
     anders
    0.49
     sajana
    0.48
    kod
    0.46
    覬
    0.45
    abhut
    0.44
     সমঝো
    0.44
     بگ
    0.43
    揸
    0.43
     وتس
    0.42
     gamanam
    0.42
    POSITIVE LOGITS
    喧
    0.54
    Like
    0.50
    R
    0.50
     Copy
    0.48
    生
    0.47
     Viol
    0.47
     cantante
    0.47
    த்தை
    0.47
    끽
    0.47
    强化
    0.46
    Activations Density 0.000%

    No Known Activations