© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 180868
    Prev
    Next
    INDEX
    Explanations

    or, how, or ... if

    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_29_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
     ignored
    0.37
     ignoring
    0.37
     উপেক্ষা
    0.37
     ignores
    0.37
    geschichte
    0.34
    畽
    0.34
     począ
    0.33
     klassischen
    0.33
     ersten
    0.32
     pelatihan
    0.32
    POSITIVE LOGITS
    桐
    0.36
     tunneling
    0.33
    ewords
    0.33
    据悉
    0.32
    声道
    0.31
    менен
    0.31
    orable
    0.31
    Words
    0.31
    ycznej
    0.31
     tunnelling
    0.31
    Activations Density 0.003%

    No Known Activations