© 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. 14678
    Prev
    Next
    INDEX
    Explanations

    verbs ending in 's', 'ing', or '-sembles' as well as the word 'broadcasts' and relates to governing or organization

    oai_token-act-pair · gemini-2.0-flash

    presentations/displays

    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
     אחת
    -0.70
    numerusform
    -0.70
    AnchorStyles
    -0.65
    Portale
    -0.64
    LookAnd
    -0.63
     صوتيه
    -0.63
    WithMany
    -0.62
    InjectAttribute
    -0.61
    SequentialGroup
    -0.61
    AndEndTag
    -0.60
    POSITIVE LOGITS
     nakalista
    0.54
     SEDS
    0.47
    nibal
    0.46
    ריכה
    0.46
    tokine
    0.45
    setStroke
    0.45
    cension
    0.45
    ardı
    0.44
    complexContent
    0.44
    ummy
    0.43
    Activations Density 1.388%

    No Known Activations