© 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. 14006
    Prev
    Next
    INDEX
    Explanations

    locations, especially those with coordinating conjunctions and punctuation

    oai_token-act-pair · gemini-2.0-flash

    Russia/Soviet Union/Asia

    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
     INVENTION
    -0.62
    theros
    -0.59
    Населення
    -0.55
    zoon
    -0.54
     الرياضيه
    -0.53
     tourmaline
    -0.52
    IBarButtonItem
    -0.52
    trophic
    -0.51
    mology
    -0.49
    loem
    -0.49
    POSITIVE LOGITS
    Rujukan
    0.70
    yntaxException
    0.65
    JpaRepository
    0.63
    oredCriteria
    0.63
    matchCondition
    0.56
     Wikimedijinoj
    0.55
    </thead>
    0.54
    بوابة
    0.51
     former
    0.51
    fscanf
    0.51
    Activations Density 1.724%

    No Known Activations