© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13512
    Prev
    Next
    INDEX
    Explanations

    names of research organizations

    oai_token-act-pair · gemini-2.0-flash

    research institutes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     AssemblyCulture
    -0.65
    enfone
    -0.63
     nahilalakip
    -0.57
    stylers
    -0.56
    orari
    -0.54
    VIAF
    -0.54
     $#
    -0.54
    thenReturn
    -0.54
    Cyfeiriadau
    -0.53
    urgy
    -0.52
    POSITIVE LOGITS
    AddHtmlAttribute
    0.63
    "}";
    0.56
     unknownFields
    0.54
     passés
    0.50
    AlterField
    0.47
     GenerationType
    0.46
    ="<?=
    0.46
     никакого
    0.46
     participaron
    0.46
    setCellStyle
    0.45
    Activations Density 1.073%

    No Known Activations