© 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. 259180
    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
     Frankly
    1.23
     Hume
    1.19
    𝘾
    1.16
     Victorian
    1.16
     CBA
    1.15
     Honestly
    1.14
     Strictly
    1.14
     Х
    1.13
    க்கொள்ள
    1.13
    𝐞
    1.12
    POSITIVE LOGITS
     revenu
    1.06
     propria
    1.04
    er
    1.04
    ר
    1.04
    differ
    1.03
     própria
    1.03
    ar
    1.02
     indebtedness
    1.01
    야
    1.01
     rapproche
    1.00
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.