© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5627
    Prev
    Next
    INDEX
    Explanations

    the word "absolute", and also sometimes the prefix "una-"

    oai_token-act-pair · gemini-2.0-flash

    absolute

    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
    PhysRevD
    -0.76
     referenties
    -0.67
     Nab
    -0.66
    spira
    -0.64
     Menlo
    -0.62
    acyl
    -0.60
    orphic
    -0.60
     Kling
    -0.59
    PhysRev
    -0.59
    tinyos
    -0.59
    POSITIVE LOGITS
     שוליים
    0.77
    RuleContext
    0.68
    __(/*!
    0.61
    setof
    0.59
    mstyle
    0.56
    WebServlet
    0.54
    исленность
    0.53
    ecake
    0.53
    AddTagHelper
    0.52
    SequentialGroup
    0.52
    Activations Density 0.786%

    No Known Activations