© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1149
    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_2_width_16k_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
    ع
    1.44
     konu
    1.25
     grond
    1.22
    daki
    1.20
    matig
    1.20
     شهر
    1.17
    ographic
    1.17
    न
    1.16
     partic
    1.15
    сього
    1.15
    POSITIVE LOGITS
    ро
    1.45
    era
    1.24
     când
    1.20
    یه
    1.15
    트워크
    1.14
     ami
    1.11
     dels
    1.11
     NAO
    1.11
     nasa
    1.11
     inception
    1.10
    Activations Density 0.002%

    No Known Activations