© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    4. 260114
    Prev
    Next
    INDEX
    Explanations

    numbers and commas

    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_22_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
     tendrás
    0.25
     ג
    0.24
    irán
    0.24
     hierro
    0.24
     ダブル
    0.23
     Prohibition
    0.23
    intage
    0.23
     Бет
    0.22
     গঙ্গ
    0.22
    rk
    0.22
    POSITIVE LOGITS
    &=
    0.24
    MacroExpansion
    0.21
    かが
    0.20
    Qr
    0.20
    Supporting
    0.20
    Janet
    0.19
    atial
    0.19
    Ada
    0.19
    Angela
    0.19
    Compart
    0.19
    Activations Density 0.002%

    No Known Activations