© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1799
    Prev
    Next
    INDEX
    Explanations

    words related to fantasy world mythology

    oai_token-act-pair · gemini-2.0-flash

    tokens with specific prefixes

    np_token-act-pair-logits · gpt-4o-mini

    Names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     CreateTagHelper
    -0.87
    tagext
    -0.77
    AnchorStyles
    -0.77
     مشين
    -0.75
     endwhile
    -0.73
     <>",
    -0.71
     informée
    -0.70
    __':
    -0.69
     '\\;'
    -0.69
    FunctionFlags
    -0.64
    POSITIVE LOGITS
     Tik
    0.46
     Peak
    0.45
     above
    0.44
    ModelAndView
    0.43
     f
    0.43
     third
    0.42
     Poli
    0.41
     entry
    0.40
     v
    0.40
     middle
    0.40
    Activations Density 0.278%

    No Known Activations