© 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. 5248
    Prev
    Next
    INDEX
    Explanations

    hexadecimal representations

    oai_token-act-pair · gemini-2.0-flash

    unique identifiers or technical terms

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

    code

    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
    imab
    -0.58
    flage
    -0.47
    atorul
    -0.44
    ctober
    -0.44
    +:+
    -0.43
    PRNewswire
    -0.43
     devez
    -0.43
     Rem
    -0.42
     Remy
    -0.42
    ليز
    -0.42
    POSITIVE LOGITS
    aarrggbb
    0.80
    SharedDtor
    0.79
    parsedMessage
    0.73
     متعلقه
    0.72
    lapsingToolbar
    0.66
    DoubleQuotes
    0.66
    verwijspagina
    0.65
    ագրություններ
    0.63
    fjspx
    0.63
    SizeF
    0.63
    Activations Density 9.261%

    No Known Activations