© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14518
    Prev
    Next
    INDEX
    Explanations

    salutations and closings in emails or forum posts

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ArrowToggle
    -0.85
     defaultstate
    -0.64
    Personensuche
    -0.57
    RetentionPolicy
    -0.54
     OnInit
    -0.52
     eccell
    -0.52
     TextAppearance
    -0.49
     sportivo
    -0.48
    {*
    -0.48
     riders
    -0.48
    POSITIVE LOGITS
    ÁRIO
    0.45
    roppo
    0.45
    ună
    0.44
    بوابة
    0.44
     Taken
    0.43
    phous
    0.42
    ariado
    0.42
    oise
    0.42
    Datuak
    0.42
    zzazione
    0.41
    Activations Density 0.231%

    No Known Activations