© 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. 9870
    Prev
    Next
    INDEX
    Explanations

    general conversational language, often related to discussing a topic (the word 'about' is a big indicator)

    oai_token-act-pair · gemini-2.0-flash

    about

    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
    I
    -0.50
    About
    -0.45
    B
    -0.44
    E
    -0.43
    P
    -0.42
    1
    -0.41
    G
    -0.40
    3
    -0.38
    -
    -0.38
    <eos>
    -0.38
    POSITIVE LOGITS
    LookAnd
    1.30
     myſelf
    1.24
    ThroughAttribute
    1.20
     themſelves
    1.16
    afficheront
    1.15
     whoſe
    1.15
     متعلقه
    1.14
    BeginInit
    1.13
     unknownFields
    1.13
     himſelf
    1.12
    Activations Density 23.868%

    No Known Activations