© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1604
    Prev
    Next
    INDEX
    Explanations

    words and phrases suggesting relationships between people

    oai_token-act-pair · gemini-2.0-flash

    say "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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     relationship
    -2.80
    Relationship
    -2.69
     relationships
    -2.67
     Relationship
    -2.64
     relation
    -2.64
     relations
    -2.61
     Relationships
    -2.59
    relationship
    -2.55
     Relation
    -2.55
    Relationships
    -2.53
    POSITIVE LOGITS
    ╝
    0.48
    </tfoot>
    0.48
    terno
    0.47
    UnsafeEnabled
    0.46
     المعيارى
    0.45
    Lexer
    0.45
    ANTLR
    0.44
    gman
    0.44
    GOTREF
    0.44
     impré
    0.44
    Activations Density 2.482%

    No Known Activations