© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9296
    Prev
    Next
    INDEX
    Explanations

    instances of the word "have" related to past actions or possibilities

    oai_token-act-pair · gemini-2.0-flash

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     HAV
    -0.51
    had
    -0.46
    yip
    -0.45
    الحياه
    -0.45
    Sucesor
    -0.45
     umana
    -0.44
    Had
    -0.42
    DoubleQuotes
    -0.42
    تقاوى
    -0.41
     habet
    -0.41
    POSITIVE LOGITS
    medriver
    0.64
    ();)
    0.64
     CreateTagHelper
    0.61
     mẽ
    0.57
    prefixes
    0.56
    })]
    0.56
     put
    0.56
    tinyos
    0.55
    hling
    0.55
    tekend
    0.54
    Activations Density 0.437%

    No Known Activations