© 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. 7704
    Prev
    Next
    INDEX
    Explanations

    phrases related to someone's timeline or career and references to the word "his"

    oai_token-act-pair · gemini-2.0-flash

    tokens related to "his" and various time or sequence words

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

    his

    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
    endphp
    -0.71
    ThroughAttribute
    -0.67
    +#+#
    -0.66
    Παραπομπές
    -0.65
    DoubleQuotes
    -0.63
     utafitiHapana
    -0.62
     صوتيه
    -0.61
    ="#">
    -0.61
    \{\\
    -0.61
    rália
    -0.60
    POSITIVE LOGITS
    UnknownFieldSet
    0.89
    Portale
    0.60
    ValueStyle
    0.52
    enteuer
    0.52
     three
    0.50
     Ceramby
    0.49
     time
    0.49
     four
    0.48
     word
    0.46
     quatre
    0.45
    Activations Density 1.512%

    No Known Activations