© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6326
    Prev
    Next
    INDEX
    Explanations

    uses of the words "is", "are", "that", "not", "which", "who", "and", "an", "be", or sometimes '-equipped'.

    oai_token-act-pair · gemini-2.0-flash

    words related to connections or relationships

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

    are

    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
    ValueGeneration
    -0.82
    expandindo
    -0.78
    aarrggbb
    -0.74
    OGND
    -0.73
    #+#
    -0.71
    AddTagHelper
    -0.71
     AssemblyCompany
    -0.69
    saraba
    -0.69
     Normdatei
    -0.68
    الحياه
    -0.66
    POSITIVE LOGITS
     linked
    0.57
     attached
    0.55
     connected
    0.55
     tied
    0.55
     related
    0.54
     awaiting
    0.54
     beside
    0.53
     beyond
    0.53
     unknown
    0.52
     critical
    0.52
    Activations Density 7.155%

    No Known Activations