© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11962
    Prev
    Next
    INDEX
    Explanations

    text referencing maps and locations

    oai_token-act-pair · gemini-2.0-flash

    say "map"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     map
    -2.95
     maps
    -2.89
     Map
    -2.89
     Maps
    -2.78
     mapping
    -2.69
    Map
    -2.63
     mapped
    -2.59
     Mapping
    -2.59
    maps
    -2.50
    map
    -2.48
    POSITIVE LOGITS
     kasarigan
    0.46
    jeka
    0.40
     légales
    0.40
     serai
    0.36
     nghi
    0.35
    Lö
    0.35
     pinulongan
    0.34
    andom
    0.34
    nvarchar
    0.33
    RemoveField
    0.33
    Activations Density 1.833%

    No Known Activations