© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7350
    Prev
    Next
    INDEX
    Explanations

    numbers followed by operators or results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_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
    urangi
    2.34
     MaxPooling
    2.34
     damn
    2.34
    ➸
    2.33
    믹
    2.30
     exchanging
    2.28
    parseFloat
    2.24
     awali
    2.20
    ために
    2.20
     conda
    2.19
    POSITIVE LOGITS
    ➢
    2.66
    <0x0D>
    2.57
    en
    2.47
     сна
    2.44
    te
    2.43
    ির
    2.38
    ጨማሪ
    2.37
     вызыва
    2.31
    picking
    2.30
     maggiori
    2.30
    Activations Density 0.127%

    No Known Activations