© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1869
    Prev
    Next
    INDEX
    Explanations

    graphical user interface elements

    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_40_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
     realised
    0.44
    yon
    0.38
    jir
    0.35
    苍
    0.34
    कार
    0.34
     freezes
    0.34
     breather
    0.34
    Office
    0.33
    phone
    0.33
    Појединачна
    0.33
    POSITIVE LOGITS
    뭍
    0.46
    ୯
    0.41
                                  
    0.41
     lanzó
    0.39
    起動
    0.39
     ,[
    0.39
    ംഗ്
    0.37
     counterv
    0.37
    ců
    0.37
     девя
    0.37
    Activations Density 0.015%

    No Known Activations