© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 246016
    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_11_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
     lovingly
    1.15
     случаи
    1.15
    𝐦
    1.14
     primers
    1.12
     palav
    1.12
     mighty
    1.10
    𝐜
    1.09
    𝐫
    1.08
     sorular
    1.07
     কাপুর
    1.06
    POSITIVE LOGITS
    den
    1.10
    was
    1.07
    owitz
    1.07
    TER
    1.03
    то
    1.02
    的路
    0.99
    ète
    0.97
    ет
    0.96
    ter
    0.96
    atie
    0.96
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.