© 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. 12711
    Prev
    Next
    INDEX
    Explanations

    the abbreviation Dr

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "Dr" followed by a name or title

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

    Dr

    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
    OGND
    -0.73
    GEBURTSDATUM
    -0.69
    principalColumn
    -0.67
     '\\;'
    -0.64
     Revision
    -0.63
    sizeCache
    -0.59
     continúas
    -0.58
     الاطلاع
    -0.57
     Revisions
    -0.57
     Himo
    -0.57
    POSITIVE LOGITS
    ClientRect
    0.52
     <=",
    0.44
    rillation
    0.43
    ছে
    0.43
     صوتيه
    0.43
     convaincre
    0.42
    Delimiter
    0.42
     Str
    0.42
    žite
    0.41
    tamo
    0.41
    Activations Density 0.549%

    No Known Activations