© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5502
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas, chemical symbols, gene sequences, equipment and processes

    oai_token-act-pair · gemini-2.0-flash

    is/has

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     are
    -1.52
     were
    -1.34
     ARE
    -1.14
    were
    -1.13
    are
    -1.10
     WERE
    -1.08
     weren
    -0.99
    Are
    -0.98
     aren
    -0.98
    Were
    -0.97
    POSITIVE LOGITS
     is
    1.02
     has
    0.90
     was
    0.89
     does
    0.80
     isn
    0.70
     hasn
    0.69
     doesn
    0.66
     continues
    0.65
     kurie
    0.63
     isnt
    0.62
    Activations Density 13.663%

    No Known Activations