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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6433
    Prev
    Next
    INDEX
    Explanations

    the word "parameters," and words relating to low cost or financial resources

    oai_token-act-pair · gemini-2.0-flash

    quantifiable conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     I
    -1.10
     
    -1.05
    ↵↵
    -1.02
     \
    -0.92
     (
    -0.91
     B
    -0.91
    ↵
    -0.90
     '
    -0.84
     V
    -0.83
     Ar
    -0.81
    POSITIVE LOGITS
     itſelf
    2.45
     Monfieur
    2.42
     Efq
    2.42
     myſelf
    2.31
     Houſe
    2.23
     whoſe
    2.11
     pleaſure
    2.09
     himſelf
    2.08
     becauſe
    2.06
     themſelves
    2.06
    Activations Density 1.337%

    No Known Activations