© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 56-GEMMASCOPE-2-TRANSCODER-262K
    4. 167052
    Prev
    Next
    INDEX
    Explanations

    proper painting

    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_56_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
     evening
    0.42
    赟
    0.41
    敢
    0.37
    सुबह
    0.37
     morning
    0.36
    ;
    0.36
     glEnable
    0.35
     Evening
    0.35
    makes
    0.35
     yılları
    0.35
    POSITIVE LOGITS
     Proper
    0.48
    Proper
    0.46
     proper
    0.46
     signalling
    0.43
     വാർത്ത
    0.42
    (":")[
    0.41
     painting
    0.41
     खबरों
    0.41
    painting
    0.39
    它的
    0.38
    Activations Density 0.004%

    No Known Activations