© 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. 8414
    Prev
    Next
    INDEX
    Explanations

    marketing language like taglines and phrases about community

    oai_token-act-pair · gemini-2.0-flash

    words related to core values

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

    core values

    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
     AssemblyCompany
    -0.81
    脚注の使い方
    -0.80
    elemField
    -0.76
     يتيمه
    -0.68
     BoxFit
    -0.68
    StructEnd
    -0.66
    WebElementEntity
    -0.66
     تضيفلها
    -0.65
    DockStyle
    -0.64
     tartalomajánló
    -0.64
    POSITIVE LOGITS
     values
    0.99
     core
    0.80
    values
    0.75
     Values
    0.75
     catch
    0.75
    core
    0.73
     tag
    0.71
     guiding
    0.70
     Core
    0.69
    Core
    0.68
    Activations Density 2.238%

    No Known Activations