© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2943
    Prev
    Next
    INDEX
    Explanations

    the name "Mary"

    oai_token-act-pair · gemini-2.0-flash

    Mary or code

    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
    SBATCH
    -0.53
     GetYourGuide
    -0.51
     Савезне
    -0.50
    ponential
    -0.49
    utsch
    -0.48
     naman
    -0.47
    wargs
    -0.47
    trun
    -0.46
    afy
    -0.46
    igi
    -0.46
    POSITIVE LOGITS
    ValueStyle
    0.73
     للمعارف
    0.61
    bootstrapcdn
    0.60
    setViewName
    0.59
     nahilalakip
    0.57
     člá
    0.56
    antMatchers
    0.56
    xase
    0.55
    ConstraintMaker
    0.54
    AsUp
    0.54
    Activations Density 0.343%

    No Known Activations