© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12890
    Prev
    Next
    INDEX
    Explanations

    words indicating difficulty or importance

    oai_token-act-pair · gemini-2.0-flash

    tasks/responsibilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     ویکی‌پدیا
    -0.68
     Mousse
    -0.59
     Sosten
    -0.56
    ngdoc
    -0.55
     Hegel
    -0.51
     écoulé
    -0.51
    amaño
    -0.50
     getResource
    -0.50
     Ninh
    -0.50
     lampada
    -0.50
    POSITIVE LOGITS
    nodoc
    0.68
     للمعارف
    0.61
    usermodel
    0.58
    Literatura
    0.55
    WriteBarrier
    0.54
    ardoor
    0.54
    orianCalendar
    0.54
    JdbcTemplate
    0.53
    TRIBUN
    0.52
    scriptcase
    0.52
    Activations Density 2.940%

    No Known Activations