© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5693
    Prev
    Next
    INDEX
    Explanations

    hardware or devices plus prepositions or articles like "a", "an", "the", "to", "from", or "through"

    oai_token-act-pair · gemini-2.0-flash

    programming terminology or coding styles

    np_token-act-pair-logits · gpt-4o-mini

    telecommunications and electronics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     Viana
    -0.51
     "");
    -0.45
     Daerah
    -0.44
     Perla
    -0.43
    erenc
    -0.42
    SOFTWARE
    -0.42
     Königin
    -0.42
    monton
    -0.42
    PC
    -0.41
    Packages
    -0.41
    POSITIVE LOGITS
    DockStyle
    0.90
    ValueStyle
    0.89
     disambiguazione
    0.83
    ItemBackground
    0.77
    modb
    0.76
    MessageTagHelper
    0.74
    ArgsConstructor
    0.71
    IsMutable
    0.71
    expandindo
    0.70
     estekak
    0.69
    Activations Density 2.251%

    No Known Activations