© 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. 15549
    Prev
    Next
    INDEX
    Explanations

    text from other languages and names of people

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages and/or code

    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
     AppCompatTheme
    -0.55
     invokingState
    -0.53
     récla
    -0.49
     rembour
    -0.48
    sigt
    -0.47
    يكب
    -0.47
     NSCoder
    -0.47
     Höhe
    -0.46
    Diweddarwch
    -0.46
     nepiecieš
    -0.46
    POSITIVE LOGITS
     houſe
    0.57
     beholder
    0.55
    MessageTagHelper
    0.52
     >=",
    0.51
     ci
    0.51
     interlocutor
    0.50
    tachment
    0.50
     <>",
    0.49
     providence
    0.49
     Wikimédia
    0.48
    Activations Density 0.847%

    No Known Activations