© 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
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 14300
    Prev
    Next
    INDEX
    Explanations

    words ending with the suffix "i". It also has a weaker association with the suffix "ini"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ක්
    -0.43
    leitung
    -0.43
    quette
    -0.42
    enska
    -0.41
    CreateModel
    -0.41
    iress
    -0.41
    jän
    -0.39
    совой
    -0.39
    createComponent
    -0.38
    |}{}
    -0.38
    POSITIVE LOGITS
    oredCriteria
    0.83
     SwitchCompat
    0.68
     vectorielle
    0.67
     []*
    0.63
     تضيفلها
    0.63
    ActionCreators
    0.63
    показания
    0.63
    oader
    0.62
     Roskov
    0.62
    Datuak
    0.62
    Activations Density 0.440%

    No Known Activations