© 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
    2. Gemma-3-27B-IT
    3. 51-GEMMASCOPE-2-TRANSCODER-262K
    4. 68524
    Prev
    Next
    INDEX
    Explanations

    valid / invalid concept

    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_51_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
    Teach
    0.84
     Teach
    0.83
    教
    0.78
     teach
    0.76
     coach
    0.70
     insegn
    0.70
     teaching
    0.70
     taught
    0.70
     教
    0.70
     обуча
    0.68
    POSITIVE LOGITS
     дій
    0.55
     చె
    0.52
    дій
    0.42
     বৈধ
    0.41
     допусти
    0.40
     செல்ல
    0.40
    ">*
    0.40
     impact
    0.38
     permissible
    0.37
    DVRIP
    0.37
    Activations Density 0.001%

    No Known Activations