© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9295
    Prev
    Next
    INDEX
    Explanations

    names of places that host and perform music, like orchestras, operas, and radio stations

    oai_token-act-pair · gemini-2.0-flash

    music and perfomances

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     commerciali
    -0.59
    ticides
    -0.56
    Personendaten
    -0.54
     Unmarshal
    -0.52
    Bibliograf
    -0.52
    RectangleBorder
    -0.52
    inate
    -0.51
     vPvB
    -0.51
     useAppContext
    -0.50
     beginnetje
    -0.49
    POSITIVE LOGITS
    IntoConstraints
    0.57
     Públicas
    0.56
     NSCoder
    0.51
    interna
    0.47
    InstanceState
    0.47
    imanapun
    0.45
    wind
    0.44
    ScopeManager
    0.43
    cemment
    0.43
     Wind
    0.43
    Activations Density 2.671%

    No Known Activations