© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1732
    Prev
    Next
    INDEX
    Explanations

    mentions of the city and state of New York

    oai_token-act-pair · gemini-2.0-flash

    occurrences of "New"

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

    New

    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
    Negative Logits
    الإنجليزية
    -0.56
     Вікіпе
    -0.54
     pareti
    -0.53
    ApiModelProperty
    -0.51
    ברס
    -0.48
     únicos
    -0.47
    StructEnd
    -0.47
    utilisons
    -0.47
    ácara
    -0.47
    ThroughAttribute
    -0.46
    POSITIVE LOGITS
    MessageOf
    0.62
    RetentionPolicy
    0.59
     Year
    0.52
     York
    0.52
    schemas
    0.52
    脚注の使い方
    0.52
    lysm
    0.51
    extAlignment
    0.51
    Espèce
    0.50
     Balance
    0.50
    Activations Density 0.284%

    No Known Activations