© 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. 3894
    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
    ेक्ट
    1.88
    ^{*
    1.82
    ERCIAL
    1.68
    𝙊
    1.67
    嵋
    1.65
     sababu
    1.65
    ^{*}}
    1.64
    য
    1.64
    कप्तान
    1.64
    ukhov
    1.63
    POSITIVE LOGITS
    c
    2.43
    pw
    2.41
    cig
    2.35
     έγινε
    2.29
    h
    2.18
    p
    2.16
    𝗮
    2.11
    t
    2.07
    㽞
    2.07
    𝗴
    2.05
    Activations Density 0.024%

    No Known Activations