© 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. 3309
    Prev
    Next
    INDEX
    Explanations

    doi links

    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
    𝐲
    1.89
    𝐭
    1.85
    üedad
    1.84
    𝐠
    1.82
     cathodic
    1.77
    𝐫
    1.77
     stmt
    1.73
     poorest
    1.72
    𝐬
    1.69
    étation
    1.67
    POSITIVE LOGITS
    u
    1.77
    mi
    1.71
    री
    1.68
    at
    1.61
    mort
    1.60
    अन्य
    1.60
    kommun
    1.59
    mn
    1.58
    ן
    1.57
    ar
    1.55
    Activations Density 0.001%

    No Known Activations