© 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. 9802
    Prev
    Next
    INDEX
    Explanations

    segments of text about a person who wants to be a caterer, but also identifies a spoon in another segment.

    oai_token-act-pair · gemini-2.0-flash

    numeric terms for "one"

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

    the number one

    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
    tinyos
    -0.65
    évaluateur
    -0.61
     للمعارف
    -0.59
    enterOuterAlt
    -0.56
    الحياه
    -0.56
    
    -0.56
    หวัด
    -0.56
     esternos
    -0.54
    󠁢
    -0.54
    MLLoader
    -0.53
    POSITIVE LOGITS
     one
    3.31
    one
    2.11
     één
    1.88
    One
    1.82
     одного
    1.73
     One
    1.70
     uno
    1.70
     satu
    1.69
     unul
    1.66
     один
    1.65
    Activations Density 2.140%

    No Known Activations