© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 279
    Prev
    Next
    INDEX
    Explanations

    text about repairing electronics

    oai_token-act-pair · gemini-2.0-flash

    disassembling electronics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    QMetaType
    -0.55
    GFR
    -0.49
    </b>
    -0.43
    ifik
    -0.41
    ServletException
    -0.41
     CreateTagHelper
    -0.40
    setViewportView
    -0.40
    WebServlet
    -0.40
    tifies
    -0.40
    ́
    -0.40
    POSITIVE LOGITS
     Efq
    0.83
     Majefty
    0.67
    ICAGO
    0.66
     $_"
    0.66
    χρι
    0.66
     Monfieur
    0.65
     houſe
    0.65
    bibfield
    0.65
    ratulations
    0.64
     iſt
    0.64
    Activations Density 2.084%

    No Known Activations