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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 12718
    Prev
    Next
    INDEX
    Explanations

    words related to time/length of experiment or graphs

    oai_token-act-pair · gemini-2.0-flash

    scientific/mathematical terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Standardization
    -0.68
    glement
    -0.66
    pana
    -0.65
     ſtand
    -0.65
     supper
    -0.65
     Blackwood
    -0.64
    TestingModule
    -0.63
     pngtree
    -0.61
     vulgaris
    -0.60
    TagMode
    -0.60
    POSITIVE LOGITS
    <bos>
    0.57
    CodedInputStream
    0.56
     progress
    0.53
     beginnetje
    0.52
     progression
    0.51
     OMIT
    0.51
    MigrationBuilder
    0.49
     progre
    0.47
    jfree
    0.44
     aus
    0.43
    Activations Density 2.842%

    No Known Activations