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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10203
    Prev
    Next
    INDEX
    Explanations

    academic citations or professional biographies

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to programming or data structures

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

    Academics and MIT

    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
    floxacin
    -0.51
    SharedCtor
    -0.50
     мәкалә
    -0.49
    ніципа
    -0.47
    insatz
    -0.46
     TOK
    -0.45
    peptide
    -0.45
     Partridge
    -0.45
    ystis
    -0.45
    /******/
    -0.44
    POSITIVE LOGITS
    AccessorTable
    0.83
    ANTLR
    0.57
    DeleteBehavior
    0.57
     ErrIntOverflow
    0.57
    BeginContext
    0.57
     EconPapers
    0.56
    MigrationBuilder
    0.55
    TemporalType
    0.52
     الحره
    0.52
    ViewById
    0.51
    Activations Density 2.270%

    No Known Activations