© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3990
    Prev
    Next
    INDEX
    Explanations

    phrases that involve a transition, obstacle or disagreement.

    oai_token-act-pair · gemini-2.0-flash

    creative expressions and themes of liberation

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

    abstract concepts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    CppCodeGen
    -0.72
     estekak
    -0.71
    abestanden
    -0.70
    initializeApp
    -0.60
    AndEndTag
    -0.58
    Viited
    -0.58
    icordia
    -0.57
     Ababa
    -0.57
    thâu
    -0.56
    SuppressMessage
    -0.55
    POSITIVE LOGITS
    BeginInit
    0.51
    HasAnnotation
    0.49
    simile
    0.45
     pre
    0.45
     childhood
    0.44
     precon
    0.44
     kỳ
    0.43
    Ồ
    0.43
    données
    0.43
     social
    0.43
    Activations Density 4.064%

    No Known Activations