© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5176
    Prev
    Next
    INDEX
    Explanations

    code snippets with curly brackets and semicolons

    oai_token-act-pair · gemini-2.0-flash

    unique identifiers or programming terms

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

    Programming syntax

    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
    جغرافيا
    -0.57
    دانشنامهٔ
    -0.57
    RectangleBorder
    -0.56
    Portale
    -0.53
    IBOutlet
    -0.52
    ")->
    -0.52
    SpringBootTest
    -0.52
    InputBorder
    -0.51
    ValueStyle
    -0.50
     looting
    -0.50
    POSITIVE LOGITS
    saraba
    0.54
    verifyException
    0.52
    зулта
    0.52
    smithy
    0.51
     Administrativna
    0.50
    മ്
    0.49
     ويكي
    0.49
    iprot
    0.48
    enterOuterAlt
    0.48
     Cau
    0.48
    Activations Density 0.872%

    No Known Activations