© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6107
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to forms, data collection, and contact information

    oai_token-act-pair · gemini-2.0-flash

    programming terminology or tokens

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

    Code/URLs

    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
    VersionUID
    -0.82
     lotes
    -0.60
    ագրություններ
    -0.60
     tetrach
    -0.59
    Regulatory
    -0.59
    KommentareTeilen
    -0.58
     mandatario
    -0.56
     Puro
    -0.54
    ولوژی
    -0.54
    #
    -0.54
    POSITIVE LOGITS
     bere
    0.43
    UrlEncoded
    0.42
    LookAnd
    0.42
    matchCondition
    0.42
     refreshToken
    0.41
     Gegenteil
    0.40
    InstrumentedTest
    0.40
    TestRunner
    0.40
    '},
    0.39
     answered
    0.38
    Activations Density 4.479%

    No Known Activations