© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4894
    Prev
    Next
    INDEX
    Explanations

    expressions about thinking and helping along with respectful legal terms

    oai_token-act-pair · gemini-2.0-flash

    help

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    CloseOperation
    -0.48
     tranquill
    -0.46
     Programme
    -0.46
    Programme
    -0.45
    İstinadlar
    -0.44
    .*")]
    -0.43
    faster
    -0.43
    ↵
    -0.41
    programme
    -0.41
     programme
    -0.41
    POSITIVE LOGITS
    writeFieldEnd
    0.97
    rungsseite
    0.85
    ReusableCell
    0.72
     ModelExpression
    0.68
    PerformLayout
    0.63
    írus
    0.63
     ujednoznacz
    0.63
     تضيفلها
    0.63
    choly
    0.63
     transfieras
    0.63
    Activations Density 1.496%

    No Known Activations