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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3490
    Prev
    Next
    INDEX
    Explanations

    colleges and universities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    ्राष्ट्रीय
    0.34
    šću
    0.33
    dır
    0.32
    ᄑ
    0.32
    蜴
    0.32
     wikip
    0.32
    াতি
    0.32
    াকিস্ত
    0.31
    ச
    0.31
     resultar
    0.31
    POSITIVE LOGITS
    College
    0.42
     University
    0.42
     College
    0.41
     Collage
    0.36
     Univ
    0.35
     Diploma
    0.35
     universitaire
    0.35
     Grad
    0.35
    University
    0.35
     college
    0.34
    Activations Density 0.056%

    No Known Activations