© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13269
    Prev
    Next
    INDEX
    Explanations

    something being defective, incorrect, or not working

    oai_token-act-pair · gemini-2.0-flash

    fail

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     imperfect
    -0.72
     defective
    -0.64
     insufficient
    -0.63
     deficiencies
    -0.61
     shortcomings
    -0.60
     imperfections
    -0.60
     inadequate
    -0.60
     disrupted
    -0.60
     failings
    -0.58
    ForRow
    -0.57
    POSITIVE LOGITS
    UnitTesting
    0.66
    లాలు
    0.63
    stateMutability
    0.63
    exitRule
    0.62
    MergeFrom
    0.62
    IntoConstraints
    0.62
     defStyleAttr
    0.58
     ElementRef
    0.58
    SBATCH
    0.57
    Tracce
    0.56
    Activations Density 2.295%

    No Known Activations