© 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. 13095
    Prev
    Next
    INDEX
    Explanations

    present-tense verbs

    oai_token-act-pair · gemini-2.0-flash

    functions or actions related to processing

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

    Removing or extracting

    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
     Up
    -0.48
    Up
    -0.47
     لع
    -0.43
     ver
    -0.43
    ⎩
    -0.43
    orianCalendar
    -0.42
    UP
    -0.42
    ups
    -0.41
    FileInputStream
    -0.40
     einzu
    -0.40
    POSITIVE LOGITS
     out
    0.90
    yntaxException
    0.84
     aside
    0.81
    IUrlHelper
    0.70
    SourceChecksum
    0.69
     apart
    0.68
    transQ
    0.68
     off
    0.68
    out
    0.66
     together
    0.65
    Activations Density 2.993%

    No Known Activations