© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12348
    Prev
    Next
    INDEX
    Explanations

    example code, code snippets or code explanations

    oai_token-act-pair · gemini-2.0-flash

    for

    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
     example
    -1.63
     examples
    -1.38
    example
    -1.30
     Examples
    -1.30
     EXAMPLE
    -1.30
     instance
    -1.30
    Example
    -1.27
     Beispiele
    -1.27
     Example
    -1.25
     Beispiel
    -1.25
    POSITIVE LOGITS
     ex
    2.77
     Ex
    2.41
    ex
    2.36
    Ex
    2.31
     EX
    2.00
    EX
    1.91
     eks
    1.33
     exh
    1.12
     exc
    0.98
    exa
    0.95
    Activations Density 3.324%

    No Known Activations