© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204159
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
     condam
    0.45
    >(
    0.42
     mash
    0.39
     minut
    0.39
     Spurs
    0.39
    得到
    0.39
     książ
    0.39
     condemned
    0.38
     ha
    0.37
     July
    0.37
    POSITIVE LOGITS
    allenges
    0.47
    ꪽ
    0.41
     앞으로
    0.39
     ELEMENTS
    0.39
     Schritte
    0.39
     Сурикова
    0.38
     Geißler
    0.38
    Sharma
    0.36
     ব্যবস্থাপনা
    0.36
    <unused373>
    0.36
    Activations Density 0.000%

    No Known Activations