© 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. 3689
    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
    व
    3.53
    <0x80>
    3.19
    "</
    3.12
    ćem
    2.99
    𝘧
    2.98
    ν
    2.96
     vows
    2.95
    
    2.93
    𝘴
    2.92
    "#
    2.85
    POSITIVE LOGITS
    <bos>
    3.64
    мпа
    2.38
    ੀ
    2.37
    Lantern
    2.34
    भाविक
    2.29
    ът
    2.26
     Substituting
    2.20
    原子炉
    2.20
    ル
    2.20
     tetrachloride
    2.18
    Activations Density 0.060%

    No Known Activations