© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14442
    Prev
    Next
    INDEX
    Explanations

    discourse markers and words related to reasoning

    oai_token-act-pair · gemini-2.0-flash

    Explanations

    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
     disambiguazione
    -1.04
     ProtoMessage
    -0.94
     Савезне
    -0.94
    contentLoaded
    -0.90
    LookAnd
    -0.88
     CreateTagHelper
    -0.84
     مرئيه
    -0.84
     nahilalakip
    -0.83
    MessageTagHelper
    -0.83
    曖昧さ回避
    -0.82
    POSITIVE LOGITS
    .
    0.53
    dır
    0.44
     nevertheless
    0.42
     lisäksi
    0.42
    داری
    0.42
    vlan
    0.42
    azo
    0.42
    The
    0.40
     dikenal
    0.40
     is
    0.40
    Activations Density 2.916%

    No Known Activations