© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14202
    Prev
    Next
    INDEX
    Explanations

    nouns relating to events, concepts, or specific objects.

    oai_token-act-pair · gemini-2.0-flash

    existence

    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
    Negative Logits
    tagHelperRunner
    -0.90
    ConstraintMaker
    -0.78
     CreateTagHelper
    -0.78
    NameInMap
    -0.75
     Normdatei
    -0.74
     Paglinawan
    -0.74
     صوتيه
    -0.73
    AndEndTag
    -0.72
    pherals
    -0.71
     colère
    -0.71
    POSITIVE LOGITS
     person
    0.69
     lot
    0.69
     few
    0.66
     little
    0.59
     single
    0.58
     couple
    0.55
     part
    0.54
     former
    0.52
     small
    0.52
     bunch
    0.52
    Activations Density 11.977%

    No Known Activations