© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5095
    Prev
    Next
    INDEX
    Explanations

    sentences describing a banana split

    oai_token-act-pair · gemini-2.0-flash

    ice cream

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ModelAdmin
    -0.66
     Jefus
    -0.61
    diabetes
    -0.60
    AndEndTag
    -0.59
     Shetterly
    -0.58
     sweeter
    -0.58
     Winder
    -0.58
     sugar
    -0.57
     Shakspeare
    -0.57
     myſelf
    -0.56
    POSITIVE LOGITS
    tvguidetime
    0.53
    UserScript
    0.49
    Suara
    0.49
    tyfik
    0.48
    клопе
    0.47
    tät
    0.47
    енча
    0.45
    Хьажоргаш
    0.45
    PreferredItem
    0.44
    arium
    0.44
    Activations Density 0.281%

    No Known Activations