© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9648
    Prev
    Next
    INDEX
    Explanations

    words related to organizations with a physical location (office, community center, etc) or other place-related concepts.

    oai_token-act-pair · gemini-2.0-flash

    places or areas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ?
    -0.81
    ?")
    -0.78
    ']").
    -0.70
     delantera
    -0.69
    "]').
    -0.67
     siguran
    -0.66
     uș
    -0.66
     jambes
    -0.66
     picioare
    -0.65
     argint
    -0.64
    POSITIVE LOGITS
     متعلقه
    0.57
    MigrationBuilder
    0.54
     it
    0.54
    NameValuePair
    0.52
     paper
    0.51
     they
    0.50
    itect
    0.49
    InstrumentedTest
    0.49
    hoea
    0.48
    __((
    0.47
    Activations Density 2.593%

    No Known Activations