© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 239893
    Prev
    Next
    INDEX
    Explanations

    starting point

    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_25_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
    चल
    0.37
     পুস্ত
    0.34
     kvalitet
    0.34
     germany
    0.34
    㖷
    0.34
    CLUDES
    0.33
     nigg
    0.33
     dodging
    0.33
     fasi
    0.32
     kval
    0.32
    POSITIVE LOGITS
     Uncle
    0.30
     관심을
    0.30
    栲
    0.30
    search
    0.29
     commod
    0.29
    Uncle
    0.29
    teach
    0.29
     Economic
    0.29
     সার্চ
    0.29
     TypeToken
    0.29
    Activations Density 0.011%

    No Known Activations