© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11876
    Prev
    Next
    INDEX
    Explanations

    verbs, especially auxiliary verbs and "doing" words, in various contexts, and some nouns that are related to planning or action.

    oai_token-act-pair · gemini-2.0-flash

    well good

    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
    fjspx
    -0.89
    клопе
    -0.81
    pushFollow
    -0.80
     <<<<<<<<<<<<<<
    -0.76
     Wikimedijinoj
    -0.75
     EconPapers
    -0.75
     viewDidLoad
    -0.74
     defaultstate
    -0.74
     onCreateView
    -0.72
    RotationOrder
    -0.72
    POSITIVE LOGITS
     well
    0.63
    well
    0.48
    saraba
    0.47
     good
    0.41
    Well
    0.41
    put
    0.39
    eting
    0.38
    ab
    0.38
    abil
    0.38
     Well
    0.37
    Activations Density 1.732%

    No Known Activations