© 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. 8739
    Prev
    Next
    INDEX
    Explanations

    how

    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
    o
    2.09
    mol
    1.76
    ente
    1.67
    े
    1.66
    なあ
    1.56
    Suppl
    1.52
    los
    1.49
     enfoque
    1.48
     পড়ুন
    1.47
    んばんは
    1.45
    POSITIVE LOGITS
    م
    2.06
     réellement
    1.84
    ʜ
    1.81
    مون
    1.74
    受信
    1.74
    ის
    1.74
     quiera
    1.73
     assertThat
    1.67
    т
    1.66
    았다
    1.65
    Activations Density 0.078%

    No Known Activations