© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139547
    Prev
    Next
    INDEX
    Explanations

    given

    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
    觀眾
    0.43
    这一点
    0.43
     بالط
    0.39
     cal
    0.38
    딱
    0.38
     pale
    0.38
     ಗೋ
    0.36
     abduction
    0.36
     balon
    0.36
     شغ
    0.36
    POSITIVE LOGITS
     fornisce
    0.43
    Así
    0.38
    Provides
    0.38
    Hvis
    0.38
    <unused342>
    0.38
    Neighbors
    0.38
     provides
    0.37
    Built
    0.37
    칩
    0.37
     hasn
    0.37
    Activations Density 0.004%

    No Known Activations