© 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. 7523
    Prev
    Next
    INDEX
    Explanations

    code snippets, specifically C-like code and Javascript loops, potentially involving memory access or data structures.

    oai_token-act-pair · gemini-2.0-flash

    Code

    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
    nocache
    -0.68
    .*")]
    -0.66
     referenties
    -0.64
    complexContent
    -0.61
    хьтан
    -0.61
     متعلقه
    -0.60
    zarchiwizowane
    -0.60
    };*/
    -0.58
    +:+
    -0.58
    MemoryWarning
    -0.58
    POSITIVE LOGITS
     ModelExpression
    0.56
    }{$\
    0.50
     AssemblyProduct
    0.49
     Chwiliwch
    0.48
    )
    0.46
    revalidate
    0.46
    同时也
    0.45
     weil
    0.44
    ätz
    0.43
     $\
    0.43
    Activations Density 4.689%

    No Known Activations