© 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. 45127
    Prev
    Next
    INDEX
    Explanations

    interested in exploring these

    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
    慷
    0.26
    स्पर्
    0.26
     spez
    0.25
    JECT
    0.25
     hydrol
    0.24
     specially
    0.24
    生意
    0.24
    egang
    0.24
    关系
    0.23
    Sap
    0.23
    POSITIVE LOGITS
     stay
    0.25
    нике
    0.25
    専
    0.24
     obedience
    0.24
     anek
    0.23
     devotee
    0.23
    ផ្ត
    0.23
     Patagonia
    0.23
     literature
    0.23
     irritated
    0.23
    Activations Density 0.013%

    No Known Activations