© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227726
    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_6_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
    n
    1.34
    k
    1.19
    f
    1.18
    ן
    1.17
    w
    1.16
    x
    1.08
    ن
    1.07
    s
    1.06
    де
    1.05
    j
    1.05
    POSITIVE LOGITS
     LISA
    0.90
    刄
    0.86
     symphony
    0.83
     Nir
    0.82
     Stru
    0.81
    ियो
    0.80
     २
    0.80
     kaleidoscopic
    0.79
     monastery
    0.78
     saxophone
    0.77
    Activations Density 0.000%

    No Known Activations