© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5336
    Prev
    Next
    INDEX
    Explanations

    code syntax and pandas dataframe manipulations

    oai_token-act-pair · gemini-2.0-flash

    specific variable assignment and function calls

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

    code and technical documentation

    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
     pinulongan
    -0.80
     surla
    -0.78
    ########.
    -0.63
    AndEndTag
    -0.63
    Externe
    -0.61
    +:+
    -0.60
     Wicidata
    -0.56
    发表于
    -0.54
    addCriterion
    -0.54
    ROW
    -0.53
    POSITIVE LOGITS
    VIAF
    0.57
    lež
    0.51
    drop
    0.47
     penghar
    0.47
    TemporalType
    0.46
     vaih
    0.46
    blame
    0.45
     kanssa
    0.45
     blame
    0.45
    WillAppear
    0.45
    Activations Density 0.947%

    No Known Activations