© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4277
    Prev
    Next
    INDEX
    Explanations

    geographic measurements, specifically those in kilometers or miles.

    oai_token-act-pair · gemini-2.0-flash

    directional geographical indicators

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

    say [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_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
     distanciation
    -0.57
    XmlType
    -0.56
     surla
    -0.54
    -------
    -0.54
     ostavi
    -0.54
    cheri
    -0.53
    chkin
    -0.52
    aronne
    -0.49
    utnik
    -0.49
    gbaar
    -0.49
    POSITIVE LOGITS
     north
    0.82
     northeast
    0.80
     east
    0.76
    north
    0.74
     southeast
    0.72
     south
    0.71
     northwest
    0.71
     southwest
    0.69
    __*/
    0.61
    south
    0.60
    Activations Density 2.705%

    No Known Activations