© 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. 14579
    Prev
    Next
    INDEX
    Explanations

    MIT license references, code licensing, and associated copyright statements

    oai_token-act-pair · gemini-2.0-flash

    terms related to coding frameworks or libraries

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

    Software licenses

    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
    脚注の使い方
    -0.67
     Lettre
    -0.54
     poursu
    -0.52
     revient
    -0.51
     Addresses
    -0.51
    Codes
    -0.50
     Codes
    -0.50
     científicas
    -0.49
     scienza
    -0.49
    code
    -0.48
    POSITIVE LOGITS
    MigrationBuilder
    0.65
     الحره
    0.65
    ValueStyle
    0.63
    SpringRunner
    0.63
    writeFieldEnd
    0.62
    ANDUM
    0.59
    crollView
    0.58
     Chwiliwch
    0.57
    derung
    0.56
    reactstrap
    0.56
    Activations Density 1.190%

    No Known Activations