© 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. 13247
    Prev
    Next
    INDEX
    Explanations

    scientific writing about particle physics

    oai_token-act-pair · gemini-2.0-flash

    Particle physics and radiation

    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
    SourceChecksum
    -0.79
     pinulongan
    -0.75
    kloped
    -0.69
    AntiForgeryToken
    -0.66
     EnglishChoose
    -0.65
    клопе
    -0.65
    曖昧さ回避
    -0.65
    rungsseite
    -0.65
    Geplaatst
    -0.64
    RenderAtEndOf
    -0.64
    POSITIVE LOGITS
     almond
    0.50
    amet
    0.45
     meta
    0.44
    TableField
    0.44
     loss
    0.44
    ipes
    0.43
     rans
    0.42
     displacement
    0.41
    sterone
    0.41
    SHIP
    0.41
    Activations Density 4.097%

    No Known Activations