© 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. 90514
    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
     Overwatch
    0.54
     Medellín
    0.51
    Finland
    0.50
     Inici
    0.50
     কোথ
    0.49
     fermion
    0.49
    OLOGIA
    0.48
    遐
    0.47
     fingerprint
    0.47
     FISA
    0.47
    POSITIVE LOGITS
     episodes
    0.43
     pernah
    0.43
    דע
    0.43
     obeys
    0.42
     lays
    0.42
    ร
    0.41
     behaves
    0.41
    દ
    0.41
    р
    0.40
     NSString
    0.40
    Activations Density 0.000%

    No Known Activations