© 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. 5791
    Prev
    Next
    INDEX
    Explanations

    French and Indian War

    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
    меча
    1.46
    (\
    1.46
    \{
    1.46
    把
    1.42
     óptica
    1.42
    க்கு
    1.40
    ﻢ
    1.36
    しも
    1.33
    了一个
    1.32
    इ
    1.29
    POSITIVE LOGITS
    <%=
    1.61
     doigts
    1.51
     tieto
    1.48
     îng
    1.45
     thiab
    1.45
    𝓻
    1.45
    ंटिक
    1.44
    лада
    1.43
    NotBlank
    1.41
     rzeczy
    1.40
    Activations Density 0.000%

    No Known Activations