© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6529
    Prev
    Next
    INDEX
    Explanations

    location details and numbers in an article about a sewing business opening a new location

    oai_token-act-pair · gemini-2.0-flash

    town selection

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    pixel
    -0.50
    NYC
    -0.44
     counties
    -0.43
    ecma
    -0.41
    дії
    -0.40
    ADELPHIA
    -0.40
     électroniques
    -0.39
     schia
    -0.39
    County
    -0.39
    жность
    -0.39
    POSITIVE LOGITS
     Select
    1.19
     select
    1.13
    Select
    1.12
    select
    1.04
     town
    1.00
     SELECT
    0.98
     Town
    0.92
     towns
    0.90
     TOWN
    0.87
    Town
    0.85
    Activations Density 1.978%

    No Known Activations