© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33033
    Prev
    Next
    INDEX
    Explanations

    email drafts

    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
     ।”
    0.46
     debacle
    0.42
    .​​
    0.41
     ​​​​
    0.40
    人士
    0.39
    ApiModel
    0.39
     गतिविधि
    0.39
    。”
    0.38
    Authorities
    0.38
    ।”
    0.38
    POSITIVE LOGITS
     poor
    0.40
     spicy
    0.37
     Â
    0.36
     어려운
    0.36
     Egyptian
    0.36
     aa
    0.35
     stranded
    0.35
     fatal
    0.35
     abnormally
    0.34
     fussy
    0.34
    Activations Density 0.115%

    No Known Activations