© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6908
    Prev
    Next
    INDEX
    Explanations

    multilingual character sequences

    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
     hijau
    2.64
    oslovens
    2.59
     thorough
    2.52
    ὲ
    2.43
     уж
    2.35
    ektedir
    2.31
    irrahim
    2.30
    ter
    2.28
    naires
    2.27
    etään
    2.27
    POSITIVE LOGITS
     Macquarie
    2.46
    𝘨
    2.45
     lapply
    2.33
    finn
    2.29
    🌐
    2.25
     ara
    2.20
    им
    2.20
    𝘩
    2.19
    HTTPSampler
    2.19
    अधिकांश
    2.16
    Activations Density 0.011%

    No Known Activations