© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218161
    Prev
    Next
    INDEX
    Explanations

    broadcast channels

    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_31_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
     stumble
    0.29
     circularly
    0.29
     वाच
    0.27
     음악
    0.27
    말
    0.27
    音樂
    0.27
    ukebox
    0.26
    managers
    0.26
     इस्ला
    0.26
     stumbled
    0.26
    POSITIVE LOGITS
     دق
    0.29
     costes
    0.29
     vehicles
    0.28
     Villiers
    0.28
    車種
    0.27
     নয়াদ
    0.27
    inales
    0.26
     AVERAGE
    0.26
    ∈</
    0.26
     तनु
    0.26
    Activations Density 0.002%

    No Known Activations