© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12270
    Prev
    Next
    INDEX
    Explanations

    code snippets mentioning removal of elements

    oai_token-act-pair · gemini-2.0-flash

    remove/delete

    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
     transfieras
    -0.79
    modelBuilder
    -0.60
    PreferredItem
    -0.56
    archiviato
    -0.54
     kaarangay
    -0.53
    +#+#
    -0.52
     vapeur
    -0.52
     gratuits
    -0.52
     تانيه
    -0.50
     érde
    -0.49
    POSITIVE LOGITS
     चीज़ों
    0.73
     NUKAT
    0.68
    chandise
    0.56
     Merchandise
    0.55
    siella
    0.54
    いぐるみ
    0.54
    ftagPool
    0.53
     Poche
    0.53
     Valerio
    0.52
    trio
    0.52
    Activations Density 5.440%

    No Known Activations