© 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. 178305
    Prev
    Next
    INDEX
    Explanations

    Therm

    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
     Επι
    0.38
     ڪر
    0.38
     merkle
    0.37
    𝚓
    0.37
     მი
    0.36
    τικού
    0.36
     TI
    0.36
     fined
    0.36
    Academy
    0.36
     Fredrik
    0.36
    POSITIVE LOGITS
    rias
    0.38
    னம்
    0.38
    antar
    0.37
    urlar
    0.37
     susceptibility
    0.36
     nanoc
    0.36
    ild
    0.35
     phóng
    0.35
    אר
    0.33
    ْنَ
    0.33
    Activations Density 0.000%

    No Known Activations