© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109008
    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_2_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
    to
    0.96
    お
    0.96
    この
    0.95
     և
    0.95
     are
    0.92
    その
    0.90
    お客
    0.89
    ス
    0.87
    ین
    0.86
    おそらく
    0.86
    POSITIVE LOGITS
    .
    1.32
    ol
    1.30
    in
    1.24
    i
    1.07
    k
    1.03
    ال
    0.98
    T
    0.94
    3
    0.93
    den
    0.89
    ili
    0.89
    Activations Density 0.000%

    No Known Activations