© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3159
    Prev
    Next
    INDEX
    Explanations

    place names and related terms like metro, river, lake, bay, county, area, shore, etc

    oai_token-act-pair · gemini-2.0-flash

    non-English terms or code-like phrases

    np_token-act-pair-logits · gpt-4o-mini

    city names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    tagext
    -0.48
    WriteBarrier
    -0.45
    ادگی
    -0.44
    uxxxx
    -0.44
    XMLSchema
    -0.44
    ATN
    -0.44
    estanding
    -0.43
    tagHelperRunner
    -0.43
     elkaar
    -0.43
    PerformLayout
    -0.43
    POSITIVE LOGITS
     }}"></
    0.68
    abetes
    0.65
     disambiguazione
    0.63
    verwijspagina
    0.57
     समीक्षाओं
    0.57
     препратки
    0.56
     betweenstory
    0.56
    FFIX
    0.56
     مشين
    0.53
    واسطة
    0.53
    Activations Density 0.606%

    No Known Activations