© 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. 22928
    Prev
    Next
    INDEX
    Explanations

    serving/evolved

    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
    糊
    0.45
    aldehyde
    0.37
     wash
    0.37
    ionale
    0.37
    נה
    0.36
    дал
    0.36
    Wash
    0.36
    ionista
    0.36
    🇪
    0.36
    ంథ
    0.35
    POSITIVE LOGITS
     UM
    0.72
     evolved
    0.65
     Serving
    0.64
     serving
    0.58
     cd
    0.54
    serving
    0.53
    Serving
    0.52
     Cd
    0.47
    Cd
    0.46
    evol
    0.46
    Activations Density 0.045%

    No Known Activations