© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 79851
    Prev
    Next
    INDEX
    Explanations

    sh

    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_53_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
    Chrom
    0.38
    gh
    0.38
    컴
    0.38
    เวอร์
    0.37
     deteriorating
    0.37
     कॉम्
    0.37
     वैलेंट
    0.37
    comer
    0.37
    aram
    0.36
     Blink
    0.36
    POSITIVE LOGITS
    EMAN
    0.46
    eman
    0.43
     adipose
    0.43
    AD
    0.42
    ল
    0.42
     Loi
    0.41
    adn
    0.41
    adne
    0.39
    مان
    0.39
     ENTRE
    0.39
    Activations Density 0.003%

    No Known Activations