© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11324
    Prev
    Next
    INDEX
    Explanations

    a mix of words and syntax from different programming languages (Portuguese and C)

    oai_token-act-pair · gemini-2.0-flash

    code and documentation

    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
    MigrationBuilder
    -0.71
    SequentialGroup
    -0.71
    󠁴
    -0.69
    MLLoader
    -0.67
     дописавши
    -0.66
    SerializedSize
    -0.64
    moiselle
    -0.60
    ynchronously
    -0.60
    uitton
    -0.60
     يتيمه
    -0.60
    POSITIVE LOGITS
     znaleźć
    0.65
     serem
    0.61
    Portály
    0.56
     uzyska
    0.56
    toBeTruthy
    0.55
     testGet
    0.55
     jesteśmy
    0.55
     powin
    0.54
     kupić
    0.52
     znajdziesz
    0.52
    Activations Density 0.321%

    No Known Activations