© 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. 39907
    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
    환
    0.49
    p
    0.49
    ｈ
    0.47
     h
    0.44
    হো
    0.44
    mig
    0.43
     philosoph
    0.43
     pouvez
    0.42
    migrate
    0.42
     migrate
    0.42
    POSITIVE LOGITS
     Dunes
    0.53
    asında
    0.52
     by
    0.52
     Cannes
    0.52
    ˹
    0.52
    GINIA
    0.51
     paddling
    0.51
    igata
    0.51
        
    0.50
    āra
    0.50
    Activations Density 0.000%

    No Known Activations