© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15411
    Prev
    Next
    INDEX
    Explanations

    words that are parts of other words, especially those related to past tense or technical jargon

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     nahilalakip
    -0.61
    addGap
    -0.60
    urlpatterns
    -0.60
     partecipazione
    -0.59
     leçon
    -0.56
     fémin
    -0.56
     prieten
    -0.55
     Económica
    -0.54
     étrang
    -0.54
    caux
    -0.53
    POSITIVE LOGITS
    umers
    0.81
     Nowadays
    0.73
     nowadays
    0.70
     wich
    0.70
    Nowadays
    0.66
     technics
    0.61
    AnchorStyles
    0.60
    ();)
    0.60
    adays
    0.59
    Lenght
    0.59
    Activations Density 4.450%

    No Known Activations