© 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. 12704
    Prev
    Next
    INDEX
    Explanations

    LaTeX code for setting up a document

    oai_token-act-pair · gemini-2.0-flash

    document-related terminology or coding syntax

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

    Latex and URLs

    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
     CreateTagHelper
    -0.50
    DrawerLayout
    -0.46
    libft
    -0.46
     createSprite
    -0.45
    髮
    -0.45
     незавершена
    -0.44
     descobri
    -0.43
     motor
    -0.42
    Kills
    -0.41
    ựa
    -0.41
    POSITIVE LOGITS
     autorytatywna
    0.78
     Réponses
    0.71
    fjspx
    0.71
    writerow
    0.63
    bewerken
    0.62
    AccessorTable
    0.60
     EconPapers
    0.57
    />";
    0.56
    ítima
    0.55
    dataclass
    0.54
    Activations Density 0.423%

    No Known Activations