© 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. 8422
    Prev
    Next
    INDEX
    Explanations

    radiating, beaming, heating

    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
    ן
    3.13
    anum
    2.51
    esi
    2.47
    ᴀ
    2.20
    ྪ
    2.15
    oze
    2.15
     ribosome
    2.15
     fuera
    2.13
    ef
    2.10
     bilayer
    2.09
    POSITIVE LOGITS
    𝒕
    2.65
    𝒊
    2.26
    𝑳
    2.24
    𝑺
    2.20
     الشمس
    2.19
    লাপ
    2.18
     aument
    2.15
    wirkung
    2.13
     Radiat
    2.11
    theon
    2.11
    Activations Density 0.060%

    No Known Activations