© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3850
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest proposing or putting forward an idea

    oai_token-act-pair · gemini-2.0-flash

    suggestions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    AutoScaleMode
    -0.62
    glEnd
    -0.59
     الدولى
    -0.59
    าล
    -0.58
     HasFactory
    -0.58
     NUKAT
    -0.57
     HttpNotFound
    -0.57
    WithIOException
    -0.57
     <=",
    -0.57
     HANDLE
    -0.56
    POSITIVE LOGITS
     propose
    1.04
    Proposed
    1.02
     proposed
    1.00
    proposed
    0.99
     proposes
    0.98
     Proposed
    0.98
     proposing
    0.97
     proposals
    0.88
     PROPOSED
    0.88
     proposal
    0.87
    Activations Density 1.257%

    No Known Activations