© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11573
    Prev
    Next
    INDEX
    Explanations

    phrases that are used to introduce an opinion or clarification

    oai_token-act-pair · gemini-2.0-flash

    negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ագրություններ
    -0.60
    transQ
    -0.59
    NameInMap
    -0.57
    ValueStyle
    -0.56
    complexType
    -0.53
    gendes
    -0.53
    istia
    -0.53
     môn
    -0.52
     David
    -0.52
    :+:
    -0.52
    POSITIVE LOGITS
    <bos>
    0.95
     Roskov
    0.69
    DeleteBehavior
    0.62
     onCancelled
    0.56
    FunctionFlags
    0.55
     useAuth
    0.52
    IUrlHelper
    0.52
     scharf
    0.51
     brancas
    0.51
     rospy
    0.50
    Activations Density 1.264%

    No Known Activations