© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218645
    Prev
    Next
    INDEX
    Explanations

    background color and text color declarations

    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_31_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
     убы
    0.47
    หยุด
    0.42
    再
    0.39
    ौज
    0.38
     волос
    0.38
     আব
    0.38
     Пусть
    0.37
    代
    0.37
    CheckBox
    0.36
    দয়
    0.36
    POSITIVE LOGITS
     containing
    0.41
     aliments
    0.36
     layouts
    0.36
     chronicles
    0.36
     cols
    0.35
     patronage
    0.35
    ronome
    0.35
     intakes
    0.35
     сило
    0.35
     solvent
    0.35
    Activations Density 0.001%

    No Known Activations