© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1508
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming language syntax

    oai_token-act-pair · gemini-2.0-flash

    Numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     ostavi
    -0.56
    PropertyChanging
    -0.54
    addKeyListener
    -0.51
    íncia
    -0.50
     يتيمه
    -0.49
    thâu
    -0.48
    NewGuid
    -0.48
    oprecipitation
    -0.48
    czyny
    -0.47
     positifs
    -0.47
    POSITIVE LOGITS
     forty
    1.20
     sixty
    1.20
     seventy
    1.16
     thirty
    1.16
     Thirty
    1.12
     fifty
    1.10
     nineteen
    1.09
    5
    1.09
    forty
    1.09
     twenty
    1.09
    Activations Density 14.881%

    No Known Activations