© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15437
    Prev
    Next
    INDEX
    Explanations

    contextual words possibly located near a number or an abbreviation

    oai_token-act-pair · gemini-2.0-flash

    Updates and explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    +#+#
    -0.89
    SharedCtor
    -0.81
    windowFixed
    -0.78
     resourceCulture
    -0.78
    IUrlHelper
    -0.77
    RegressionTest
    -0.76
    StructEnd
    -0.74
     ProtoMessage
    -0.74
    exitRule
    -0.73
    SharedDtor
    -0.72
    POSITIVE LOGITS
     It
    0.53
    <eos>
    0.44
     We
    0.43
    вър
    0.42
     (
    0.42
    it
    0.41
     S
    0.41
    creva
    0.41
    It
    0.40
    hetti
    0.40
    Activations Density 3.284%

    No Known Activations