© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11326
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and logic statements, as well as personality

    oai_token-act-pair · gemini-2.0-flash

    concluding words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Pristupljeno
    -0.54
    ніципалі
    -0.52
     vectorielles
    -0.52
     passés
    -0.52
     maux
    -0.50
     passée
    -0.50
     breathed
    -0.50
     ModelExpression
    -0.49
     verwijzen
    -0.49
     financières
    -0.48
    POSITIVE LOGITS
     states
    0.81
    SharedDtor
    0.76
     concludes
    0.73
     leads
    0.71
    ates
    0.71
    states
    0.66
     progresses
    0.66
     covers
    0.66
     repeats
    0.66
     declares
    0.65
    Activations Density 5.582%

    No Known Activations