© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12798
    Prev
    Next
    INDEX
    Explanations

    words that connect clauses such as 'that', 'to', 'from', and 'with'

    oai_token-act-pair · gemini-2.0-flash

    long, complex sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    __*/
    -0.51
     unbedingt
    -0.47
     Qu
    -0.46
     Formerly
    -0.46
     neces
    -0.45
     living
    -0.44
    =-=-=-=-
    -0.44
    findpost
    -0.44
     NECESS
    -0.44
     ces
    -0.44
    POSITIVE LOGITS
    FunctionFlags
    0.79
    AddTagHelper
    0.75
    <bos>
    0.74
     propOrder
    0.73
    AutoScale
    0.71
    IsMutable
    0.68
     ainfi
    0.65
     archers
    0.64
     degradability
    0.61
     ویکی‌پدیا
    0.61
    Activations Density 16.928%

    No Known Activations