© 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. 14129
    Prev
    Next
    INDEX
    Explanations

    academic citations and names with initials.

    oai_token-act-pair · gemini-2.0-flash

    Scientific research paper

    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
     oni
    -0.42
     in
    -0.42
    ima
    -0.41
     organelles
    -0.37
    bis
    -0.37
    Mouse
    -0.37
     GNU
    -0.36
     Leich
    -0.36
     anatom
    -0.35
     UITableView
    -0.35
    POSITIVE LOGITS
     CreateTagHelper
    1.19
    AndEndTag
    1.01
    Tembelea
    0.99
    rungsseite
    0.96
     виправивши
    0.90
    Personendaten
    0.87
    OGND
    0.85
     متحده
    0.82
    帖最后由
    0.79
     متعلقه
    0.79
    Activations Density 1.064%

    No Known Activations