© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12761
    Prev
    Next
    INDEX
    Explanations

    journalistic contexts that present facts, such as those found in a news agency

    oai_token-act-pair · gemini-2.0-flash

    News articles/reporting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     wireType
    -0.54
     Cataloging
    -0.51
    }{*}{
    -0.48
    Wide
    -0.46
     lenker
    -0.46
    gaze
    -0.46
    SourceChecksum
    -0.46
    intios
    -0.46
    utilisons
    -0.45
    +#+#
    -0.45
    POSITIVE LOGITS
     يتيمه
    0.65
     faſt
    0.59
     uſed
    0.58
    douard
    0.57
    ViewImports
    0.57
     becauſe
    0.56
    heide
    0.55
     raiſ
    0.54
     FontWeight
    0.53
    DoubleQuotes
    0.53
    Activations Density 1.493%

    No Known Activations