© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11100
    Prev
    Next
    INDEX
    Explanations

    terms related to performances and tours

    oai_token-act-pair · gemini-2.0-flash

    tour or shows

    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
     Italijanski
    -0.82
    UnsafeEnabled
    -0.82
    клопе
    -0.81
     Paglinawan
    -0.80
     CreateTagHelper
    -0.79
     الرياضيه
    -0.78
     <<<<<<<<<<<<<<
    -0.75
     protoimpl
    -0.74
    ]")]
    -0.74
    Personendaten
    -0.72
    POSITIVE LOGITS
    pageX
    0.47
     håller
    0.41
    pozorn
    0.40
    rstrip
    0.40
     ragazzo
    0.39
    itect
    0.39
     yalnız
    0.39
     last
    0.39
     صوتيه
    0.39
     Last
    0.38
    Activations Density 0.241%

    No Known Activations