© 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. 57067
    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
    t
    0.62
     invertebr
    0.59
    т
    0.55
    л
    0.54
     intensidade
    0.53
     galore
    0.52
     loạt
    0.52
    ان
    0.51
     ascor
    0.50
     afficher
    0.50
    POSITIVE LOGITS
    ا
    0.67
    riol
    0.52
    zeitig
    0.52
    els
    0.51
     ৩
    0.50
     kidnapping
    0.49
    ेक्स
    0.49
    PAS
    0.48
    (".",
    0.48
    爹
    0.47
    Activations Density 0.000%

    No Known Activations