© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1318
    Prev
    Next
    INDEX
    Explanations

    the phrase "way to" or similar constructions, sometimes in a business context

    oai_token-act-pair · gemini-2.0-flash

    way/means

    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
    BeginContext
    -0.70
    WithMany
    -0.65
    tagext
    -0.59
     multiplication
    -0.58
     مشارکت‌کنندگان
    -0.57
    WriteLiteral
    -0.56
    thenReturn
    -0.54
     esercit
    -0.53
    RepeatedField
    -0.53
     minOccurs
    -0.52
    POSITIVE LOGITS
    <bos>
    0.80
    anon
    0.57
     ويكيپيديا
    0.56
    ⓧ
    0.56
    piecze
    0.53
    ngu
    0.53
     дописавши
    0.51
    ーブ
    0.49
    carpa
    0.49
    :][
    0.48
    Activations Density 2.259%

    No Known Activations