© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3441
    Prev
    Next
    INDEX
    Explanations

    big fan of

    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_5_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
    आइ
    0.54
     aws
    0.54
    olução
    0.54
    浗
    0.54
    ্তিক
    0.52
     gras
    0.52
     holomorphic
    0.52
     euphoria
    0.51
    ciudad
    0.51
     nudge
    0.50
    POSITIVE LOGITS
     notepad
    0.59
     ab
    0.54
     dign
    0.52
     calificaciones
    0.51
    #!/
    0.51
    ativo
    0.50
    ².
    0.50
     दर्
    0.49
     人気
    0.49
     eines
    0.49
    Activations Density 0.003%

    No Known Activations