© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 209264
    Prev
    Next
    INDEX
    Explanations

    file extension is

    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_19_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
    !(
    0.39
     graz
    0.38
     Caj
    0.38
     Out
    0.38
     Wol
    0.38
    《
    0.38
    £
    0.38
    {\
    0.37
     gorgeous
    0.37
     Bic
    0.37
    POSITIVE LOGITS
    mortem
    0.42
    ProjectPath
    0.39
    ûn
    0.38
    stadt
    0.37
    ować
    0.37
    飕
    0.37
    boom
    0.36
    ર્ટ
    0.36
    енты
    0.36
    ﺓ
    0.36
    Activations Density 0.002%

    No Known Activations