© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210947
    Prev
    Next
    INDEX
    Explanations

    staying updated/informed

    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_20_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
    waż
    0.46
     थी
    0.45
    闶
    0.45
     vaccinated
    0.43
    চ্ছি
    0.43
     अस्पताल
    0.41
    म्मेदारी
    0.41
    Obviously
    0.41
    ąda
    0.41
     automated
    0.41
    POSITIVE LOGITS
    unico
    0.44
     በር
    0.42
     الَّذ
    0.41
     కీలక
    0.40
    ={(
    0.40
    ഊ
    0.39
     endeavours
    0.39
     compreender
    0.39
    lds
    0.38
    //=
    0.38
    Activations Density 0.001%

    No Known Activations