© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4863
    Prev
    Next
    INDEX
    Explanations

    place names and subsequent descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    o
    2.08
    zione
    1.91
    ла
    1.91
     hasattr
    1.86
    꼴
    1.82
    zelfde
    1.72
    cip
    1.71
    cional
    1.71
    液
    1.67
    l
    1.63
    POSITIVE LOGITS
    ش
    2.82
     어느
    2.59
    ि
    2.46
     virial
    2.31
    िं
    2.20
     Rodrigo
    2.16
     просты
    2.07
     riparian
    2.07
    方を
    2.07
    បង្
    2.06
    Activations Density 0.012%

    No Known Activations