© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10906
    Prev
    Next
    INDEX
    Explanations

    phrases related to problems, benefits, or authority

    oai_token-act-pair · gemini-2.0-flash

    forms of "lay"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Efq
    -0.87
    Liefs
    -0.84
    évaluateur
    -0.83
    OGND
    -0.80
     purpoſe
    -0.79
     Jefus
    -0.78
     myſelf
    -0.75
    ंदीखरीदारी
    -0.74
    Groetjes
    -0.72
    astéroïdes
    -0.72
    POSITIVE LOGITS
     laid
    0.79
     lays
    0.71
     laying
    0.52
     L
    0.48
     l
    0.47
     Lay
    0.46
    L
    0.45
     Laid
    0.43
     str
    0.43
    l
    0.41
    Activations Density 3.786%

    No Known Activations