© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12228
    Prev
    Next
    INDEX
    Explanations

    references to locations, particularly cardinal directions and their associated place names

    oai_token-act-pair · gemini-2.0-flash

    cardinal directions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    abá
    -0.54
    COUVER
    -0.50
    ouds
    -0.50
    SequentialGroup
    -0.49
    posedge
    -0.49
    myk
    -0.48
    koi
    -0.47
     regata
    -0.45
     Utility
    -0.44
     correctes
    -0.44
    POSITIVE LOGITS
    PreferredItem
    0.69
    NameInMap
    0.67
    AutoScaleMode
    0.59
    存于互联网档案馆
    0.59
    djangoproject
    0.56
    adpleegd
    0.55
    aarrggbb
    0.55
     TType
    0.54
    Tikang
    0.53
    iprot
    0.53
    Activations Density 0.283%

    No Known Activations