© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 259581
    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_10_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
     Sağ
    1.19
    বন
    1.12
    lp
    1.10
    ber
    1.08
    ব
    1.06
    QCD
    1.05
     Orthodox
    1.01
    ۥ
    1.00
     Sebab
    1.00
    ので
    0.99
    POSITIVE LOGITS
    stuffs
    1.36
    payload
    1.26
    खोरी
    1.25
     redonde
    1.25
    橥
    1.24
    dropDown
    1.24
    calcular
    1.23
     griff
    1.21
    дам
    1.18
     sprinkling
    1.17
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.