© 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. 77054
    Prev
    Next
    INDEX
    Explanations

    locations, place names, states

    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
    祥
    0.36
     ditches
    0.35
     Gora
    0.35
     nonempty
    0.35
    スペ
    0.35
     gehörte
    0.35
     spectator
    0.34
     Falconer
    0.34
     espectáculo
    0.34
     verifiable
    0.34
    POSITIVE LOGITS
    asy
    0.36
    azine
    0.35
    aty
    0.35
    aiti
    0.35
    㸵
    0.35
    함
    0.34
    zt
    0.34
    ardust
    0.34
    岀
    0.34
    }{
    0.33
    Activations Density 0.000%

    No Known Activations