© 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. 7726
    Prev
    Next
    INDEX
    Explanations

    react component state

    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
    犸
    2.63
    ad
    2.49
    しまう
    2.44
    д
    2.39
    𝐍
    2.38
    ia
    2.35
    an
    2.33
    ergic
    2.29
    um
    2.27
    ט
    2.27
    POSITIVE LOGITS
    र
    2.58
    вості
    2.45
    feito
    2.31
    𝓷
    2.31
    ことを
    2.30
    ッテリー
    2.28
    ătoare
    2.27
     metų
    2.27
    𝓸
    2.24
    鵡
    2.24
    Activations Density 0.001%

    No Known Activations