© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12776
    Prev
    Next
    INDEX
    Explanations

    proper nouns, often those of computer programs, devices, or other software

    oai_token-act-pair · gemini-2.0-flash

    XP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     reason
    -0.58
     REASON
    -0.56
     reasons
    -0.54
    astify
    -0.52
     Reason
    -0.52
    englanniksi
    -0.51
     Mait
    -0.51
    reason
    -0.50
    ●●
    -0.49
    면
    -0.48
    POSITIVE LOGITS
    offsetof
    0.68
     InputDecoration
    0.67
    XmlSchema
    0.66
    uxxxx
    0.66
    bootstrapcdn
    0.64
     BorderRadius
    0.61
    ParallelGroup
    0.59
    SourceChecksum
    0.56
    dropIfExists
    0.56
    ToAction
    0.52
    Activations Density 1.296%

    No Known Activations