© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46125
    Prev
    Next
    INDEX
    Explanations

    path or of

    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_22_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
     unwavering
    0.26
    𒂍
    0.24
     understated
    0.24
     underwhelming
    0.24
     unapolog
    0.24
    มนเชสเตอร์
    0.23
    า
    0.23
    ഗ്
    0.23
    नांतर
    0.22
     நேற்று
    0.22
    POSITIVE LOGITS
     usługi
    0.26
     dyeing
    0.24
     visitation
    0.24
     govern
    0.24
     Triton
    0.23
     użyt
    0.23
     gubern
    0.23
     sorption
    0.23
     chitin
    0.22
     taxon
    0.22
    Activations Density 0.004%

    No Known Activations