© 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. 3822
    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
    spir
    1.43
     RequestMethod
    1.30
    ncol
    1.29
    le
    1.28
    ように
    1.28
     typesetting
    1.28
    વ
    1.26
     oxide
    1.24
    fontSize
    1.23
    ll
    1.22
    POSITIVE LOGITS
    as
    1.63
    ات
    1.46
    asjon
    1.38
     deviates
    1.32
    asjoner
    1.24
     Fällen
    1.24
    espa
    1.23
     inget
    1.22
    ゃ
    1.21
    en
    1.20
    Activations Density 0.005%

    No Known Activations