© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 203115
    Prev
    Next
    INDEX
    Explanations

    intervals with recovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
     boarding
    0.41
     monta
    0.39
     Discipline
    0.38
     Belmont
    0.38
    ियल
    0.38
    纪
    0.37
     satur
    0.36
    хом
    0.36
    ंतर
    0.35
    attam
    0.35
    POSITIVE LOGITS
     sprint
    0.49
     wax
    0.47
    🎿
    0.42
    wax
    0.41
     skiers
    0.41
     paraffin
    0.41
     waxes
    0.40
    ್ರೀ
    0.38
     anvil
    0.38
     grooms
    0.38
    Activations Density 0.003%

    No Known Activations