© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153228
    Prev
    Next
    INDEX
    Explanations

    contrast

    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_23_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
    ulus
    0.45
    we
    0.39
     crow
    0.39
     vo
    0.39
     в
    0.38
     т
    0.38
     вы
    0.38
    ис
    0.37
     aktor
    0.37
     we
    0.37
    POSITIVE LOGITS
    จัดการ
    0.39
    +"
    0.39
     Renata
    0.39
    bergement
    0.38
    スタル
    0.38
    ꒪
    0.38
    ╯
    0.37
     აქვს
    0.37
     ^{
    0.36
    NK
    0.36
    Activations Density 0.014%

    No Known Activations