© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4386
    Prev
    Next
    INDEX
    Explanations

    website URLs and punctuation

    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_40_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
     Caul
    0.11
     خص
    0.11
     stra
    0.10
     imper
    0.10
    ></
    0.10
     Imper
    0.10
     hands
    0.10
     same
    0.10
     majority
    0.10
    ர்க்க
    0.10
    POSITIVE LOGITS
     پیسې
    0.13
    玠
    0.12
    ັ້ນ
    0.12
     Счетчик
    0.12
     എത്തി
    0.12
    してきました
    0.11
    idcoin
    0.11
     پیسہ
    0.11
     impulsar
    0.11
     پیپلز
    0.11
    Activations Density 0.316%

    No Known Activations