© 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. 12430
    Prev
    Next
    INDEX
    Explanations

    instances of stating assumptions or allegations

    oai_token-act-pair · gemini-2.0-flash

    state

    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
    Viitteet
    -0.83
    Personendaten
    -0.82
    expandindo
    -0.79
    Amicalement
    -0.79
    RectangleBorder
    -0.79
     Paglinawan
    -0.78
     BorderRadius
    -0.78
     itſelf
    -0.74
    adaptiveStyles
    -0.72
     AssemblyCulture
    -0.72
    POSITIVE LOGITS
     declare
    0.66
     declared
    0.60
     declares
    0.57
     claimed
    0.57
     stating
    0.55
     Declare
    0.54
     berkata
    0.54
     imply
    0.53
     declaring
    0.53
    PLAIN
    0.52
    Activations Density 0.646%

    No Known Activations