© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13925
    Prev
    Next
    INDEX
    Explanations

    Java GUI-related keywords

    oai_token-act-pair · gemini-2.0-flash

    programming syntax elements and functions

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

    =

    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
     
    -1.27
    1
    -0.65
     ۱
    -0.53
     ১
    -0.51
    gonic
    -0.48
    SharedDtor
    -0.47
    softc
    -0.45
    Unmarshal
    -0.44
    сла
    -0.43
     XNUMX
    -0.43
    POSITIVE LOGITS
    IntoConstraints
    0.82
    存于互联网档案馆
    0.76
     Roskov
    0.76
     مشين
    0.73
     שוליים
    0.69
     متعلقه
    0.68
    قایناق‌لار
    0.64
     chi̍t
    0.64
     الحره
    0.63
     Мексичка
    0.63
    Activations Density 1.301%

    No Known Activations