© 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-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 2812
    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
    ب
    2.62
    tz
    2.42
    Р
    2.40
    nh
    2.30
     goodwill
    2.27
    tick
    2.25
     thrones
    2.24
    دة
    2.23
    camb
    2.22
    ー
    2.21
    POSITIVE LOGITS
    ductory
    2.75
    ীয়
    2.53
    вет
    2.50
    Pale
    2.31
     пожалуйста
    2.27
     thirds
    2.25
    $-\
    2.24
    %>%
    2.19
     Crore
    2.19
    𝙡
    2.18
    Activations Density 0.002%

    No Known Activations