© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59221
    Prev
    Next
    INDEX
    Explanations

    good listener

    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_11_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
    the
    0.54
    D
    0.54
    ലെ
    0.52
    Three
    0.51
    A
    0.51
     Sequence
    0.50
    6
    0.50
    R
    0.50
    ernos
    0.49
    Ab
    0.48
    POSITIVE LOGITS
     appunto
    0.64
     änd
    0.61
     herv
    0.60
     cárc
    0.60
    aik
    0.57
     ahorro
    0.55
     a
    0.55
     vaisse
    0.55
     акаде
    0.54
     electrodes
    0.54
    Activations Density 0.004%

    No Known Activations