© 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. 12451
    Prev
    Next
    INDEX
    Explanations

    code snippets and associated terms like "return" and "expect".

    oai_token-act-pair · gemini-2.0-flash

    return

    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
     Normdatei
    -0.86
     فريبيس
    -0.79
    complexContent
    -0.76
    存于互联网档案馆
    -0.74
    ImageContext
    -0.72
    borderSide
    -0.68
    JpaRepository
    -0.68
    /*:
    -0.65
    دانشنامهٔ
    -0.65
    Hochspringen
    -0.65
    POSITIVE LOGITS
    H
    0.47
    intios
    0.43
    G
    0.42
    F
    0.42
    My
    0.41
    NamedQueries
    0.41
    toString
    0.41
    usiai
    0.41
     sebelah
    0.41
    rep
    0.40
    Activations Density 4.298%

    No Known Activations