© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 146473
    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_59_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
    USE
    0.44
    .**
    0.40
    edited
    0.38
    inl
    0.37
    rev
    0.37
    ンプー
    0.36
     .:
    0.36
    学
    0.36
     Use
    0.36
    :**
    0.36
    POSITIVE LOGITS
    Comm
    0.43
     زیادہ
    0.41
     }^{(
    0.41
     વધુ
    0.40
     ज़्यादा
    0.38
     ①
    0.38
     Comm
    0.38
     more
    0.36
     अधिक
    0.36
     εδώ
    0.36
    Activations Density 0.000%

    No Known Activations