© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3758
    Prev
    Next
    INDEX
    Explanations

    location changes and related words, along with some grammatical constructs.

    oai_token-act-pair · gemini-2.0-flash

    Minus

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     elevated
    -1.05
     increased
    -1.05
     increase
    -1.01
     rising
    -1.00
     higher
    -1.00
     Elevated
    -0.99
     rise
    -0.98
     upward
    -0.98
     increases
    -0.97
    Increased
    -0.97
    POSITIVE LOGITS
     rédu
    0.55
     réduite
    0.54
     moins
    0.53
    MINUS
    0.51
     menor
    0.51
     poniżej
    0.50
     minimale
    0.49
     Minus
    0.47
     menos
    0.47
     menores
    0.47
    Activations Density 1.751%

    No Known Activations