© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4380
    Prev
    Next
    INDEX
    Explanations

    language related to people and places, especially when indicating movement or location

    oai_token-act-pair · gemini-2.0-flash

    Locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     arşivlendi
    -0.53
    opol
    -0.45
     espèce
    -0.44
    ndice
    -0.42
    onViewCreated
    -0.41
     ujednoznacz
    -0.40
     stessi
    -0.40
    dirkan
    -0.39
    dags
    -0.39
    ="@+
    -0.39
    POSITIVE LOGITS
     places
    1.09
     corners
    0.91
    places
    0.86
     parts
    0.85
     PLACES
    0.85
     Places
    0.83
     somewhere
    0.82
    tagHelperRunner
    0.81
     areas
    0.81
     locations
    0.80
    Activations Density 1.501%

    No Known Activations