© 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. 40436
    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
    0.54
    ed
    0.53
    5
    0.50
    U
    0.49
    Hom
    0.47
    য়নের
    0.47
    F
    0.46
    Ghana
    0.45
    A
    0.44
    Inst
    0.44
    POSITIVE LOGITS
     externo
    0.59
     critérios
    0.59
     âmbito
    0.56
     culturale
    0.54
     întreb
    0.54
     méthod
    0.54
     debería
    0.53
     zdję
    0.53
     metodologia
    0.53
     pis
    0.52
    Activations Density 0.000%

    No Known Activations