© 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. 12948
    Prev
    Next
    INDEX
    Explanations

    sentences that have a lot of common words like "the", "that", and "of".

    oai_token-act-pair · gemini-2.0-flash

    explanations and descriptions

    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
     gehad
    -0.55
    表
    -0.51
     åren
    -0.46
     sociétés
    -0.45
    venda
    -0.44
     deepened
    -0.43
     financière
    -0.42
     società
    -0.42
     volet
    -0.42
     deepen
    -0.42
    POSITIVE LOGITS
     JpaRepository
    0.72
    AutoScale
    0.72
    
    0.71
    Архівовано
    0.69
     AssemblyTitle
    0.67
    EDEFAULT
    0.66
     AssemblyCompany
    0.63
    RectangleBorder
    0.61
    DockStyle
    0.61
    ENEFITS
    0.61
    Activations Density 1.665%

    No Known Activations