© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11696
    Prev
    Next
    INDEX
    Explanations

    words and phrases that occur in scientific writing, especially those related to reasoning

    oai_token-act-pair · gemini-2.0-flash

    high

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     مرئيه
    -0.82
    providedIn
    -0.75
     jScrollPane
    -0.66
    RenderAtEndOf
    -0.63
    tagHelperRunner
    -0.59
    tangentMode
    -0.59
     ivelany
    -0.59
     חיצוניים
    -0.59
    
    -0.58
    
    -0.56
    POSITIVE LOGITS
     high
    3.28
    high
    2.91
    High
    2.59
     High
    2.48
     higher
    2.34
    HIGH
    2.16
     low
    2.14
     HIGH
    2.13
    higher
    2.05
    高
    2.02
    Activations Density 8.746%

    No Known Activations