© 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. 11419
    Prev
    Next
    INDEX
    Explanations

    numerical sequences, especially those related to memory and bit architectures

    oai_token-act-pair · gemini-2.0-flash

    the number four

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

    6

    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
    sizeCache
    -0.59
     ब्रेकडाउन
    -0.58
     <<<<<<<<<<<<<<
    -0.54
    XmlEnum
    -0.53
     defaultstate
    -0.53
     eight
    -0.52
    findpost
    -0.51
     nahilalakip
    -0.51
    HomeAsUpEnabled
    -0.51
    CppCodeGen
    -0.50
    POSITIVE LOGITS
    4
    0.88
     fourth
    0.73
    ৪
    0.65
    Fourth
    0.62
     Fourth
    0.59
    四
    0.59
    fourth
    0.56
    ۴
    0.56
     quatrième
    0.56
    ４
    0.55
    Activations Density 1.924%

    No Known Activations