© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 22422
    Prev
    Next
    INDEX
    Explanations

    computation

    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
     Components
    0.43
    Components
    0.41
     ASSEM
    0.40
    GB
    0.40
    K
    0.38
    components
    0.38
    smoking
    0.38
     Soundtrack
    0.37
    ('/
    0.36
    THIS
    0.36
    POSITIVE LOGITS
     писал
    0.42
    是什么
    0.41
     ఉంది
    0.41
     oppress
    0.41
     foresee
    0.39
     spelen
    0.39
     কোথায়
    0.38
     why
    0.37
     पचा
    0.37
     gehört
    0.37
    Activations Density 0.002%

    No Known Activations