© 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. 2877
    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
     불구하고
    3.29
    ்
    2.80
    uq
    2.76
    een
    2.76
     thể
    2.71
    ்ய
    2.70
    ل
    2.68
     solitons
    2.64
    ordinary
    2.62
    }$
    2.56
    POSITIVE LOGITS
    ্স
    2.90
    υ
    2.90
    로
    2.68
    に
    2.60
    nSamples
    2.52
     toBe
    2.51
    nous
    2.42
    ύ
    2.42
    ণে
    2.40
    ica
    2.39
    Activations Density 0.013%

    No Known Activations