© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10359
    Prev
    Next
    INDEX
    Explanations

    articles and prepositions appearing together in text

    oai_token-act-pair · gemini-2.0-flash

    terms related to planning or scheduling

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

    things that are planned

    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
    Datuak
    -0.95
    tagHelperRunner
    -0.85
    ########.
    -0.84
    OGND
    -0.73
     MainAxisSize
    -0.73
    AndEndTag
    -0.71
     الحره
    -0.68
    SharedCtor
    -0.67
    curacies
    -0.66
    MigrationBuilder
    -0.65
    POSITIVE LOGITS
     planned
    1.66
     prescribed
    1.39
     scheduled
    1.38
     agreed
    1.33
     specified
    1.28
    planned
    1.25
     intended
    1.25
     designed
    1.24
     designated
    1.23
     predicted
    1.19
    Activations Density 6.858%

    No Known Activations