© 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. 14519
    Prev
    Next
    INDEX
    Explanations

    locations or groups of people

    oai_token-act-pair · gemini-2.0-flash

    Nigeria or Washington, D.C

    np_max-act · gemini-2.0-flash

    locations

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    WebElementEntity
    -0.74
    tvguidetime
    -0.71
    WEBPACK
    -0.70
     مشين
    -0.69
    formik
    -0.66
     Roskov
    -0.65
    ReusableCell
    -0.60
     &___
    -0.60
    :✨
    -0.60
    konos
    -0.59
    POSITIVE LOGITS
    <bos>
    2.36
     the
    0.76
    '
    0.66
    ↵↵
    0.60
    ’
    0.54
     to
    0.52
     is
    0.49
    the
    0.48
    The
    0.44
     a
    0.43
    Activations Density 2.245%

    No Known Activations