© 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. 10517
    Prev
    Next
    INDEX
    Explanations

    elements of need, and ways/abilities to overcome a challenge.

    oai_token-act-pair · gemini-2.0-flash

    words related to assistance and needs

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

    Financial problems

    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
    sizeCache
    -0.61
     समीक्षाएं
    -0.60
     CreateTagHelper
    -0.59
    DockStyle
    -0.56
    msgSender
    -0.56
    BeginInit
    -0.56
    hibli
    -0.56
     mence
    -0.55
     BrowserModule
    -0.54
    migrationBuilder
    -0.54
    POSITIVE LOGITS
     refill
    0.50
    ddots
    0.46
    '}>
    0.45
    IInterface
    0.42
     soprav
    0.41
     Italij
    0.41
    zelf
    0.41
     mined
    0.40
    marshaller
    0.40
     fill
    0.40
    Activations Density 1.453%

    No Known Activations