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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8882
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and chemical symbols

    oai_token-act-pair · gemini-2.0-flash

    Scientific/technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    A
    -0.57
    B
    -0.55
    P
    -0.55
    D
    -0.52
    S
    -0.52
    C
    -0.52
    T
    -0.51
    F
    -0.51
    E
    -0.51
     A
    -0.50
    POSITIVE LOGITS
    asgi
    0.53
    DEPORTES
    0.50
    SEGUIR
    0.48
     millet
    0.46
     UIFont
    0.45
    ITERATURE
    0.45
     sari
    0.44
     tulle
    0.44
     azy
    0.44
     ibid
    0.43
    Activations Density 6.512%

    No Known Activations