© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7059
    Prev
    Next
    INDEX
    Explanations

    places in Toronto, Canada and numbers from dates and addresses

    oai_token-act-pair · gemini-2.0-flash

    non-English names or terms

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

    cities and 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_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
    posedge
    -0.52
     _$
    -0.48
    extField
    -0.47
    GroupLayout
    -0.47
    InputBorder
    -0.47
    PRF
    -0.45
    serde
    -0.45
    neous
    -0.44
     invokingState
    -0.43
    teilungen
    -0.42
    POSITIVE LOGITS
    adina
    0.59
    جغرافيا
    0.59
    .(*
    0.54
    mbic
    0.54
    帖最后由
    0.54
    knecht
    0.53
    تقاوى
    0.52
     hâte
    0.52
    Breite
    0.51
    Atsauces
    0.50
    Activations Density 0.987%

    No Known Activations