© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14112
    Prev
    Next
    INDEX
    Explanations

    mostly last names of people

    oai_token-act-pair · gemini-2.0-flash

    research citations

    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
     ModelExpression
    -1.41
     nakalista
    -1.27
     betweenstory
    -1.24
    MigrationBuilder
    -1.21
    Personensuche
    -1.21
    хьтан
    -1.20
     ſtate
    -1.19
     myſelf
    -1.16
    IUrlHelper
    -1.16
    GEBURTSDATUM
    -1.16
    POSITIVE LOGITS
     A
    0.54
     "
    0.50
     (
    0.49
     
    0.47
    <eos>
    0.47
     K
    0.46
     “
    0.46
     T
    0.45
     \
    0.45
     $\
    0.44
    Activations Density 1.139%

    No Known Activations