© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201180
    Prev
    Next
    INDEX
    Explanations

    markets and Research

    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_12_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
    s
    0.64
    ❤️
    0.61
    4
    0.59
    ')
    0.58
    were
    0.55
    ام
    0.55
    เป็น
    0.55
    ă
    0.54
     Opinions
    0.54
    ę
    0.54
    POSITIVE LOGITS
     utilization
    0.60
     curricular
    0.60
     dimensionality
    0.56
    штар
    0.55
    γχ
    0.54
    ਸ਼
    0.53
     utilizes
    0.53
     hyperglycemia
    0.53
     pervasive
    0.53
     leverage
    0.52
    Activations Density 0.000%

    No Known Activations