© 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. 2868
    Prev
    Next
    INDEX
    Explanations

    words and phrases about relationships or connections including inverse or direct relationships

    oai_token-act-pair · gemini-2.0-flash

    specific relationships and correlations

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

    relationship

    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
     between
    -0.80
     Between
    -0.73
    between
    -0.73
     inter
    -0.68
     между
    -0.66
    Between
    -0.64
    之间
    -0.63
     BETWEEN
    -0.58
    之间的
    -0.58
     across
    -0.56
    POSITIVE LOGITS
    帖最后由
    0.63
     DHA
    0.62
     nitrite
    0.59
     Offisielt
    0.58
    GeneratedMessage
    0.58
     dreamstime
    0.57
     trumpets
    0.57
    UseVisualStyle
    0.57
     didst
    0.56
     polycarbonate
    0.55
    Activations Density 3.602%

    No Known Activations