© 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. 2832
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ality
    1.26
    t
    1.20
    it
    1.12
    lijke
    1.09
    tive
    1.02
    tion
    1.02
    tan
    0.97
    ందూ
    0.95
    不然
    0.94
    ду
    0.94
    POSITIVE LOGITS
    𝘳
    1.10
    Ε
    1.08
    Α
    1.04
     sensação
    1.02
    ɖ
    1.02
    𝗿
    1.02
     हूँ
    1.01
    𝗜
    0.99
     caiu
    0.99
     वीं
    0.98
    Activations Density 0.023%

    No Known Activations