© 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
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10806
    Prev
    Next
    INDEX
    Explanations

    instances of the prefix "lo".

    oai_token-act-pair · gemini-2.0-flash

    lo

    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
    parametrize
    -0.57
    IActionResult
    -0.56
    道
    -0.56
    stretchr
    -0.53
    Демографія
    -0.52
    IBinder
    -0.50
     thereto
    -0.50
    éli
    -0.49
    liston
    -0.49
    AttributeSet
    -0.48
    POSITIVE LOGITS
    Personendaten
    0.80
     سكانية
    0.76
    hyrchwyd
    0.66
    tagHelperRunner
    0.65
    Cyfeiriadau
    0.55
     Jefus
    0.54
     gawas
    0.52
    InitVars
    0.52
    ftagPool
    0.52
    AnchorTagHelper
    0.51
    Activations Density 0.395%

    No Known Activations