© 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. 8272
    Prev
    Next
    INDEX
    Explanations

    unicode characters, particularly those starting with \\u

    oai_token-act-pair · gemini-2.0-flash

    sequences of numbers and letters

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

    technical/scientific texts

    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
    XmlAccessorType
    -0.87
    RegistryLite
    -0.80
    AndEndTag
    -0.78
     समीक्षक
    -0.76
    featureID
    -0.74
    tagHelperRunner
    -0.70
    verwijspagina
    -0.70
     '\\;'
    -0.68
    nodoc
    -0.67
    AccessorTable
    -0.67
    POSITIVE LOGITS
     quad
    0.43
     -
    0.42
     half
    0.41
    ź
    0.41
    щ
    0.40
     autor
    0.40
     Liv
    0.40
    udin
    0.39
    endiri
    0.39
     recv
    0.39
    Activations Density 0.815%

    No Known Activations