© 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. 2882
    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
    aan
    1.24
    <=>
    1.24
    ructural
    1.14
    ių
    1.13
    aient
    1.12
    `${
    1.10
    1.08
    ong
    1.08
     व्याख्या
    1.08
    াৰ
    1.07
    POSITIVE LOGITS
    selves
    1.79
    ㄴ
    1.61
     lemmas
    1.49
    taxon
    1.43
    ships
    1.33
     "&#
    1.31
     basePath
    1.28
    coverageStat
    1.28
     CONN
    1.28
     stuffs
    1.28
    Activations Density 0.002%

    No Known Activations