© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211973
    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_5_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
    I
    1.18
    cción
    1.05
    1.03
    am
    0.96
    amme
    0.92
     \
    0.90
    ue
    0.89
    kke
    0.88
    imed
    0.88
    kommen
    0.87
    POSITIVE LOGITS
     to
    1.82
    то
    1.55
    a
    1.52
    是
    1.49
    o
    1.42
    ات
    1.41
    e
    1.38
    에
    1.38
    ير
    1.32
    으로
    1.32
    Activations Density 0.000%

    No Known Activations