© 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. 8807
    Prev
    Next
    INDEX
    Explanations

    install dependencies

    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
    सभी
    1.27
    и
    1.21
     lucru
    1.17
    ка
    1.09
    䒑
    1.08
    менно
    1.06
    TODO
    1.06
    Ꮄ
    1.05
     tack
    1.04
    ᴄ
    1.04
    POSITIVE LOGITS
     inadmissible
    1.11
     RNN
    1.11
     zippers
    1.08
    oop
    1.07
     additives
    1.06
     CLL
    1.05
    mates
    1.04
    ᚕ
    1.03
    makers
    1.03
    .³
    1.03
    Activations Density 0.005%

    No Known Activations