© 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. 8969
    Prev
    Next
    INDEX
    Explanations

    announcements, dates/times, and words related to lawsuits, medicine, or collaboration.

    oai_token-act-pair · gemini-2.0-flash

    references to announcements or updates

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

    announce

    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
    -0.53
    Up
    -0.48
    up
    -0.46
    atori
    -0.45
    ic
    -0.44
    пта
    -0.44
     Up
    -0.44
    п
    -0.44
    一つ
    -0.43
    пти
    -0.43
    POSITIVE LOGITS
     protoimpl
    0.75
    Personendaten
    0.74
    Personensuche
    0.71
    FormTagHelper
    0.70
     EconPapers
    0.68
     PyLong
    0.67
    تقاوى
    0.64
     переписи
    0.64
    ViewFeatures
    0.60
    ")->
    0.60
    Activations Density 3.279%

    No Known Activations