© 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. 14559
    Prev
    Next
    INDEX
    Explanations

    a 't' following a negation of 'is'

    oai_token-act-pair · gemini-2.0-flash

    Technical conversation snippets

    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
    AndEndTag
    -1.02
    ValueStyle
    -0.84
    Personendaten
    -0.76
    ſelf
    -0.73
    findpost
    -0.69
    NameInMap
    -0.69
    DockStyle
    -0.69
    IUrlHelper
    -0.68
     noDo
    -0.68
    Tikang
    -0.68
    POSITIVE LOGITS
     שוליים
    0.45
    nut
    0.44
    piram
    0.42
     comples
    0.38
     Fau
    0.38
    ಣ
    0.38
     Réponses
    0.38
    rind
    0.37
    setInt
    0.37
    iree
    0.36
    Activations Density 1.610%

    No Known Activations