© 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. 2708
    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
    𝘂
    2.40
    mogorov
    2.36
    しまい
    2.36
    ٢
    2.31
    men
    2.17
    buty
    2.15
    𝗶
    2.11
    ی
    2.11
    me
    2.09
    মূলক
    2.08
    POSITIVE LOGITS
    ти
    3.87
     Dazu
    2.93
    스는
    2.64
    스가
    2.58
    و
    2.57
     leeway
    2.53
     ardından
    2.53
     entail
    2.50
    스의
    2.48
     searchable
    2.45
    Activations Density 0.045%

    No Known Activations