© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31724
    Prev
    Next
    INDEX
    Explanations

    and

    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_50_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
     fair
    0.52
     Fair
    0.48
    Fair
    0.45
     Monitoring
    0.44
     Fairmont
    0.44
     Fairness
    0.43
    槛
    0.42
    ConformanceMode
    0.41
    kung
    0.41
    fair
    0.40
    POSITIVE LOGITS
    DSA
    0.41
    Washington
    0.39
    Wash
    0.39
     пя
    0.38
    要因
    0.38
     washout
    0.37
     né
    0.36
    ூழ
    0.35
    洗
    0.34
     四
    0.34
    Activations Density 0.005%

    No Known Activations