© 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. 2688
    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
    taker
    0.55
    sided
    0.52
    skii
    0.52
    ib
    0.51
    sides
    0.50
    ted
    0.49
    to
    0.48
    с
    0.48
    owed
    0.48
    sku
    0.47
    POSITIVE LOGITS
    ва
    0.59
    い
    0.54
    Pentru
    0.51
    er
    0.50
     län
    0.50
     mich
    0.48
    িতে
    0.48
    कोरोना
    0.48
     och
    0.47
    इस
    0.47
    Activations Density 0.000%

    No Known Activations