© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6566
    Prev
    Next
    INDEX
    Explanations

    job postings and restaurant reviews giving addresses.

    oai_token-act-pair · gemini-2.0-flash

    geographic locations or areas

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

    Locations and addresses

    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
    
    -0.67
    Lähteet
    -0.65
    yelitis
    -0.63
    RegressionTest
    -0.60
    DIPSETTING
    -0.57
    oa̍t
    -0.56
    tagHelperRunner
    -0.55
     esternos
    -0.54
    principalColumn
    -0.52
    IMPORTED
    -0.52
    POSITIVE LOGITS
     King
    0.59
     Upper
    0.58
     Kings
    0.57
     Old
    0.56
     downtown
    0.55
     Lower
    0.54
     Central
    0.53
     West
    0.53
    VertexArray
    0.53
     South
    0.52
    Activations Density 2.802%

    No Known Activations