© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13133
    Prev
    Next
    INDEX
    Explanations

    questions and quantifiers, particularly "how many?"

    oai_token-act-pair · gemini-2.0-flash

    questions about quantity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    Cuánto
    -0.69
     What
    -0.69
     what
    -0.67
     hoeveel
    -0.64
    What
    -0.61
    Combien
    -0.60
     cuánto
    -0.60
    Qué
    -0.59
    TypeOf
    -0.59
    Whose
    -0.57
    POSITIVE LOGITS
    Geplaatst
    0.78
     Савезне
    0.69
    存于互联网档案馆
    0.69
    tamment
    0.68
    HtmlAttribute
    0.68
     InputDecoration
    0.68
    reciated
    0.66
    soever
    0.66
    setVerticalGroup
    0.65
    enderror
    0.64
    Activations Density 1.879%

    No Known Activations