© 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. 12986
    Prev
    Next
    INDEX
    Explanations

    references to locations and the relationships between them

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to data or programming

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

    Locations

    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
     along
    -0.79
     ALONG
    -0.72
     Along
    -0.70
     entlang
    -0.67
    Along
    -0.67
    沿
    -0.66
     lungo
    -0.64
    along
    -0.61
    antism
    -0.52
    inesis
    -0.51
    POSITIVE LOGITS
    afficheront
    0.68
    AndEndTag
    0.67
    AccessorTable
    0.63
     ProtoMessage
    0.62
    utnik
    0.62
    Personendaten
    0.59
    Enllaços
    0.57
    MessageOf
    0.57
    featureID
    0.56
    envolvimento
    0.56
    Activations Density 0.781%

    No Known Activations