© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 259119
    Prev
    Next
    INDEX
    Explanations

    plot figure or imshow

    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
    YE
    0.44
     transitioned
    0.43
    WELL
    0.42
    अंतर
    0.41
     متحدہ
    0.40
    NEAR
    0.39
    }*/
    0.38
    etiti
    0.38
     localised
    0.38
    เวอร์
    0.37
    POSITIVE LOGITS
     Quadrat
    0.43
     diagrams
    0.38
     chall
    0.37
     manures
    0.37
    satz
    0.37
     ዘዴ
    0.36
     כבר
    0.36
    削
    0.36
     groups
    0.36
     Groups
    0.36
    Activations Density 0.001%

    No Known Activations