© 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. 15457
    Prev
    Next
    INDEX
    Explanations

    complicated sentences where someone struggles to figure out when and how to disagree with an organization

    oai_token-act-pair · gemini-2.0-flash

    breaking

    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
    rungsseite
    -0.87
     resourceCulture
    -0.79
    دانشنامهٔ
    -0.65
    GEBURTSDATUM
    -0.61
     kaynağından
    -0.60
    qrstuvwxyz
    -0.59
    BufferException
    -0.58
     Fichier
    -0.58
    الإنجليزية
    -0.58
     مواليد
    -0.56
    POSITIVE LOGITS
     break
    1.56
    break
    1.45
     breaking
    1.44
     breaks
    1.35
     Break
    1.30
     broke
    1.28
    breaking
    1.26
    Break
    1.26
     Breaking
    1.22
     broken
    1.19
    Activations Density 2.527%

    No Known Activations