© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1734
    Prev
    Next
    INDEX
    Explanations

    technical concepts in computer science research papers

    oai_token-act-pair · gemini-2.0-flash

    specific

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    HasForeignKey
    -0.71
    ########.
    -0.68
    setViewportView
    -0.60
    UnusedPrivate
    -0.55
     ModelExpression
    -0.54
    
    -0.54
    StoryboardSegue
    -0.53
    tvguidetime
    -0.52
    Tikang
    -0.52
    发表于
    -0.51
    POSITIVE LOGITS
     specific
    2.94
     Specific
    2.72
    Specific
    2.63
    specific
    2.48
     SPECIFIC
    2.23
     particular
    2.19
    SPECIFIC
    2.16
     específico
    2.13
     spécifique
    2.08
     específica
    2.05
    Activations Density 9.366%

    No Known Activations