© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15698
    Prev
    Next
    INDEX
    Explanations

    locations and roads in the United States in relation to other places combined with keywords associated with trails

    oai_token-act-pair · gemini-2.0-flash

    Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ChromeDriver
    -0.47
    rildi
    -0.47
     bew
    -0.47
    moveToFirst
    -0.45
     habit
    -0.45
    abinieri
    -0.44
    Lindo
    -0.44
    éal
    -0.44
    templateUrl
    -0.44
    zule
    -0.43
    POSITIVE LOGITS
    IsContent
    0.77
    脚注の使い方
    0.75
     المعيارى
    0.71
    ContentAsync
    0.70
     >=",
    0.66
    abestanden
    0.64
     незавершена
    0.64
     iprot
    0.63
     חיצוניים
    0.62
     متعلقه
    0.62
    Activations Density 3.372%

    No Known Activations