© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11726
    Prev
    Next
    INDEX
    Explanations

    words related to temporary office positions and potentially incomplete actions

    oai_token-act-pair · gemini-2.0-flash

    temporary roles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    fjspx
    -0.71
     مشين
    -0.66
    Personensuche
    -0.66
     AssemblyTitle
    -0.61
    styleType
    -0.60
    Билгалдахарш
    -0.57
     الرياضيه
    -0.56
    addCriterion
    -0.56
    مصادر
    -0.55
    fvar
    -0.55
    POSITIVE LOGITS
    CloseOperation
    0.58
    avut
    0.54
    setdefault
    0.52
    enderror
    0.50
     quelcon
    0.50
    씀
    0.49
     tocado
    0.49
    WriteTagHelper
    0.49
    oughlin
    0.48
     citoy
    0.46
    Activations Density 1.445%

    No Known Activations