© 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. 2260
    Prev
    Next
    INDEX
    Explanations

    computer code error messages with tracebacks, and text relating to slavery and agriculture

    oai_token-act-pair · gemini-2.0-flash

    the word 'last'

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

    last

    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
     насељу
    -0.65
    ISupport
    -0.65
     дописавши
    -0.52
     BrowserModule
    -0.52
     ―――――
    -0.51
    Portail
    -0.51
    GOTREF
    -0.48
    WebServlet
    -0.48
     ↓,
    -0.47
    weiser
    -0.47
    POSITIVE LOGITS
     last
    2.44
    last
    2.11
     Last
    1.89
    Last
    1.85
     LAST
    1.83
     último
    1.76
    LAST
    1.70
     últimos
    1.63
     última
    1.58
     letzten
    1.56
    Activations Density 2.136%

    No Known Activations