© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8015
    Prev
    Next
    INDEX
    Explanations

    articles that contain the word "in" followed by a year

    oai_token-act-pair · gemini-2.0-flash

    references to past events

    np_token-act-pair-logits · gpt-4o-mini

    past

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     CreateTagHelper
    -0.60
    setDo
    -0.60
    aarrggbb
    -0.59
    usstsein
    -0.59
    BoxLayout
    -0.56
    gegeven
    -0.55
    Bref
    -0.55
    "?>
    -0.54
    setVerticalGroup
    -0.54
    ittà
    -0.53
    POSITIVE LOGITS
     past
    2.78
     previous
    2.33
    past
    2.20
    Past
    2.11
    previous
    1.96
     Past
    1.92
    Previous
    1.84
     PAST
    1.83
     Previous
    1.80
     prior
    1.80
    Activations Density 4.125%

    No Known Activations