© 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. 8838
    Prev
    Next
    INDEX
    Explanations

    New Mexico

    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
    ज
    3.03
    age
    2.91
    ड
    2.85
    אן
    2.74
    etin
    2.74
    rounded
    2.71
    etary
    2.67
    これで
    2.65
    fabs
    2.61
    िक
    2.57
    POSITIVE LOGITS
    𝑝
    3.24
    𝑠
    3.02
     circumstances
    2.89
    𝑀
    2.76
    𝑆
    2.76
    𝑖
    2.71
    𝑛
    2.65
    𝐴
    2.65
     brak
    2.63
    𝐸
    2.63
    Activations Density 0.012%

    No Known Activations