© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3725
    Prev
    Next
    INDEX
    Explanations

    do, did, does

    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_40_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
    ハン
    0.38
    होस्
    0.38
    可能性がある
    0.36
    Dane
    0.36
    ubhav
    0.35
    hitva
    0.34
    せず
    0.34
    ܦ
    0.34
    ڑ
    0.34
    ების
    0.33
    POSITIVE LOGITS
     did
    1.37
     does
    1.36
     do
    1.27
    does
    1.18
    did
    1.14
     DID
    1.14
     DOES
    1.07
    Does
    1.02
     Does
    1.01
     Did
    0.96
    Activations Density 0.402%

    No Known Activations