© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5565
    Prev
    Next
    INDEX
    Explanations

    * (list of things)

    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_39_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
     ধু
    0.33
    eld
    0.31
     confluence
    0.30
     converging
    0.30
     обучение
    0.29
    Aux
    0.29
    和平
    0.29
    区
    0.28
    cci
    0.28
    ocz
    0.28
    POSITIVE LOGITS
    qttr
    0.37
     lazy
    0.36
     уг
    0.36
    ättre
    0.34
     lingk
    0.33
     meilleure
    0.33
     анато
    0.33
    จริงๆ
    0.33
     odmah
    0.33
     xt
    0.33
    Activations Density 0.230%

    No Known Activations