© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13931
    Prev
    Next
    INDEX
    Explanations

    place names

    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
     salt
    0.41
     fac
    0.40
     Salt
    0.39
    icato
    0.37
     geprüft
    0.36
     earning
    0.35
    孚
    0.35
    甸
    0.34
    禳
    0.34
     Kub
    0.34
    POSITIVE LOGITS
     فن
    0.42
     stim
    0.36
    URLConnection
    0.36
     উপকারী
    0.36
     Mend
    0.36
    Ме
    0.35
    িকালে
    0.35
    setWindowTitle
    0.35
    Finn
    0.35
    フィス
    0.35
    Activations Density 0.011%

    No Known Activations