© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 165172
    Prev
    Next
    INDEX
    Explanations

    days, presence, nexus, air

    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_13_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
    t
    0.35
     channels
    0.33
     intervened
    0.33
    halb
    0.32
     octave
    0.32
    channel
    0.32
     shrimps
    0.31
    tea
    0.31
     Zanzibar
    0.31
     വിവാ
    0.31
    POSITIVE LOGITS
    㽞
    0.35
     힘들
    0.34
     daño
    0.33
     الأد
    0.33
     تباہ
    0.32
     etti
    0.32
    欳
    0.31
    stackpath
    0.31
     देता
    0.31
     wre
    0.30
    Activations Density 0.003%

    No Known Activations