© 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
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8175
    Prev
    Next
    INDEX
    Explanations

    the prefix "imp"

    oai_token-act-pair · gemini-2.0-flash

    imp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     يتيمه
    -1.22
     utafitiHapana
    -1.17
     متعلقه
    -1.16
    LookAnd
    -1.16
     surla
    -1.15
    MigrationBuilder
    -1.14
     للاسماء
    -1.13
    ValueStyle
    -1.11
     BoxFit
    -1.11
    ьаж
    -1.10
    POSITIVE LOGITS
    '
    0.65
     
    0.62
     several
    0.56
     hard
    0.56
     in
    0.54
     left
    0.54
     system
    0.53
    ↵↵
    0.53
    вую
    0.52
     two
    0.51
    Activations Density 2.387%

    No Known Activations