© 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. 259633
    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
     prestar
    1.35
    lovely
    1.26
     presta
    1.24
     algod
    1.24
     casamento
    1.24
    웰
    1.19
    Personendaten
    1.19
    i
    1.16
    aggable
    1.16
     normales
    1.14
    POSITIVE LOGITS
     τη
    1.46
    クトル
    1.14
    ый
    1.09
    騷
    1.09
     UINT
    1.07
     fact
    1.07
    ための
    1.06
     trouble
    1.05
    յան
    1.04
     ли
    1.03
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.