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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16071
    Prev
    Next
    INDEX
    Explanations

    words and character sequences in a language other than English

    oai_token-act-pair · gemini-2.0-flash

    pod

    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
    awtextra
    -0.81
    #+#
    -0.69
    Mutagenicity
    -0.66
    __":
    -0.66
     propOrder
    -0.66
    SourceChecksum
    -0.65
    GeneratedCode
    -0.65
    WebElementEntity
    -0.65
    __":
    -0.64
    thenia
    -0.63
    POSITIVE LOGITS
     interface
    0.77
     interfaces
    0.70
    INTERFACE
    0.63
    interface
    0.62
     Interface
    0.62
    interfaces
    0.57
     INTERFACE
    0.55
    Interface
    0.54
    Interfaces
    0.52
     Interfaces
    0.52
    Activations Density 0.223%

    No Known Activations