© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9566
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to relationships, ratios, and relative measurements.

    oai_token-act-pair · gemini-2.0-flash

    relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     betweenstory
    -0.78
    ագրություններ
    -0.78
    EndContext
    -0.67
    ApiProperty
    -0.66
     виправивши
    -0.66
    migrationBuilder
    -0.66
    GOTREF
    -0.65
    BeginContext
    -0.65
    UnsafeEnabled
    -0.62
    Lähteet
    -0.61
    POSITIVE LOGITS
     relationship
    1.22
     Relationship
    1.08
    relationship
    1.07
     relationships
    1.04
     RELATIONSHIP
    1.02
     relations
    0.99
    Relationship
    0.98
     relation
    0.92
     Relationships
    0.91
    RELATION
    0.88
    Activations Density 1.397%

    No Known Activations