© 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. 11327
    Prev
    Next
    INDEX
    Explanations

    various verbs that mean to emerge or be somewhere, often "come" or some kind of movement

    oai_token-act-pair · gemini-2.0-flash

    come

    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
     come
    -2.48
    Come
    -2.11
     Come
    -2.08
    come
    -2.00
     COME
    -1.90
     comes
    -1.82
    COME
    -1.60
     came
    -1.45
    comes
    -1.41
     Comes
    -1.40
    POSITIVE LOGITS
     propOrder
    0.71
    adaptiveStyles
    0.71
    Hauptartikel
    0.70
     Roskov
    0.62
    MigrationBuilder
    0.59
    ($__
    0.58
    참고
    0.57
    oneofs
    0.57
     дописавши
    0.57
    Personendaten
    0.57
    Activations Density 4.805%

    No Known Activations