© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10003
    Prev
    Next
    INDEX
    Explanations

    names starting with "Raj" or "Rad" or "Ray" or "Ralph"

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the name "Raj"

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

    Raj/Ray

    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
    lyde
    -0.50
     ideal
    -0.45
     Katalog
    -0.44
    صد
    -0.44
    Lj
    -0.43
    CAPTCHA
    -0.43
     surla
    -0.43
    原始内容存档
    -0.43
     critical
    -0.43
    rita
    -0.42
    POSITIVE LOGITS
     Administrativna
    0.74
     Италијани
    0.71
    FunctionFlags
    0.69
     المعيارى
    0.68
    tagHelperRunner
    0.68
    GEBURTSDATUM
    0.68
    oredCriteria
    0.67
    ImageContext
    0.66
    ukone
    0.65
    transQ
    0.65
    Activations Density 0.310%

    No Known Activations