© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6528
    Prev
    Next
    INDEX
    Explanations

    passages about community involvement and support

    oai_token-act-pair · gemini-2.0-flash

    community

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Przypisy
    -0.59
     nave
    -0.49
    országban
    -0.48
    oa̍t
    -0.47
     ELECTRO
    -0.46
     plasmid
    -0.45
    myapplication
    -0.45
    żdż
    -0.45
    uelan
    -0.44
     незавершена
    -0.44
    POSITIVE LOGITS
     community
    1.23
     communities
    1.16
     communauté
    1.11
     communautés
    0.99
    community
    0.98
    communities
    0.95
     comunidade
    0.94
     comunidades
    0.93
     comunidad
    0.90
     COMMUNITY
    0.90
    Activations Density 0.678%

    No Known Activations