© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8720
    Prev
    Next
    INDEX
    Explanations

    the letters 'n', 'a', or 'y' in the middle of words or phrases

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     mendatang
    -0.53
    ChildScrollView
    -0.53
     manquer
    -0.50
     genoux
    -0.47
    vaux
    -0.46
    olm
    -0.46
     použití
    -0.46
     împre
    -0.45
     sanitaires
    -0.44
     sanitarias
    -0.44
    POSITIVE LOGITS
     on
    1.76
     On
    1.50
    On
    1.41
     ON
    1.38
    OnThe
    1.09
    onthe
    1.08
    บน
    1.04
     vpon
    1.02
    オン
    0.99
     على
    0.97
    Activations Density 0.347%

    No Known Activations