© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134408
    Prev
    Next
    INDEX
    Explanations

    when you're ready

    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_37_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
    dorff
    0.39
     realizing
    0.39
     uiteindelijk
    0.38
    醍
    0.37
     отве
    0.37
     putting
    0.36
     Wide
    0.36
     MANAG
    0.36
     답
    0.36
     Eventually
    0.35
    POSITIVE LOGITS
    does
    0.63
     did
    0.62
     does
    0.59
    did
    0.56
    Does
    0.48
     Does
    0.46
     Did
    0.44
    Did
    0.43
     do
    0.41
    出一个
    0.40
    Activations Density 0.004%

    No Known Activations