© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 2347
    Prev
    Next
    INDEX
    Explanations

    I think

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
     bells
    0.39
     cv
    0.36
     Frem
    0.36
     Bells
    0.35
    >);
    0.33
     bell
    0.33
    ่วน
    0.33
    -])
    0.33
     OR
    0.33
    សា
    0.33
    POSITIVE LOGITS
     creo
    1.68
     glaube
    1.63
     tror
    1.45
     думаю
    1.45
     penso
    1.29
     acho
    1.27
    Creo
    1.27
    だと思います
    1.25
    だと思う
    1.22
    我想
    1.21
    Activations Density 0.282%

    No Known Activations