© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1015
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    не
    2.80
    何度
    2.19
     bijection
    2.19
    ㇂
    2.06
    𝐧
    2.05
     prosecution
    2.04
     μέσω
    2.02
     casualties
    1.99
    ن
    1.98
    ל
    1.95
    POSITIVE LOGITS
     acquainted
    2.31
    ا
    2.24
    ்க
    2.12
    ם
    2.09
    merged
    2.02
     sobą
    2.01
    sair
    1.99
    tener
    1.94
     زمانہ
    1.93
     ות
    1.92
    Activations Density 0.022%

    No Known Activations