© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236375
    Prev
    Next
    INDEX
    Explanations

    announcement of release or launch

    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_32_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
     Changes
    0.39
    ğa
    0.39
    ോട്
    0.39
     možnost
    0.38
     cuộc
    0.38
    新たな
    0.37
    ཾ
    0.37
     DR
    0.37
     Möglichkeiten
    0.36
    ]*
    0.36
    POSITIVE LOGITS
    utors
    0.40
    િજા
    0.38
    itsky
    0.38
    vier
    0.36
    alassem
    0.36
    ビング
    0.35
    obank
    0.35
    ক্ষিত
    0.35
    破
    0.34
     debut
    0.34
    Activations Density 0.001%

    No Known Activations