© 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. 8086
    Prev
    Next
    INDEX
    Explanations

    words associated with plans, scheduling, and requests

    oai_token-act-pair · gemini-2.0-flash

    words related to planning or arrangements

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

    arrangements

    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
    UnusedPrivate
    -0.94
    bootstrapcdn
    -0.84
    numerusform
    -0.78
    BeginContext
    -0.77
    SourceChecksum
    -0.76
     незавершена
    -0.72
    tonsoft
    -0.71
    awtextra
    -0.71
    ValueStyle
    -0.69
    complexContent
    -0.68
    POSITIVE LOGITS
     arrangements
    1.34
    arrange
    1.13
     arrangement
    1.08
     arrang
    1.02
     plans
    1.00
     Arrangements
    0.98
     ARRANG
    0.98
     arrange
    0.96
     Arrangement
    0.94
    arrangement
    0.94
    Activations Density 0.719%

    No Known Activations