© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4956
    Prev
    Next
    INDEX
    Explanations

    Error messages

    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
    гант
    1.69
    𝘪
    1.67
    assertArg
    1.66
     Кстати
    1.54
    𝘭
    1.53
    িখিত
    1.51
     convertirse
    1.48
    o
    1.47
    ن
    1.47
    ૬
    1.45
    POSITIVE LOGITS
    ्
    1.74
    제
    1.68
    専
    1.65
    loser
    1.65
     количестве
    1.53
    ми
    1.53
     peroxide
    1.52
    제가
    1.52
    у
    1.51
     ira
    1.47
    Activations Density 0.309%

    No Known Activations