© 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. 215515
    Prev
    Next
    INDEX
    Explanations

    San Francisco landmarks

    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
    支
    0.48
     Mississippi
    0.42
    랭
    0.41
     सौंपी
    0.41
    安
    0.40
    अनु
    0.39
     अनु
    0.38
    鄢
    0.38
    நிய
    0.38
     Annu
    0.37
    POSITIVE LOGITS
     lodged
    0.43
    εδ
    0.41
    atam
    0.40
     Nobles
    0.40
    ahana
    0.39
    udra
    0.38
    agma
    0.37
    Eureka
    0.36
    akura
    0.36
     Lombard
    0.36
    Activations Density 0.001%

    No Known Activations