© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 137892
    Prev
    Next
    INDEX
    Explanations

    package.json version

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
     GoObject
    0.37
    Reed
    0.37
     freeing
    0.35
    яви
    0.35
    eden
    0.34
     hoti
    0.34
    +|\
    0.34
     pinching
    0.34
    腾
    0.34
    GREES
    0.33
    POSITIVE LOGITS
    JS
    0.46
     trabalh
    0.44
     JS
    0.44
     المق
    0.43
     AAU
    0.42
     Durham
    0.41
     Quy
    0.41
     SMP
    0.41
     IPS
    0.40
     AA
    0.39
    Activations Density 0.000%

    No Known Activations