© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14644
    Prev
    Next
    INDEX
    Explanations

    the fragment "ter" in a word

    oai_token-act-pair · gemini-2.0-flash

    Ter

    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
    مصادر
    -0.61
    THISDAY
    -0.54
    تقاوى
    -0.53
    PRWEB
    -0.52
     snippetHide
    -0.51
     devriez
    -0.51
    casio
    -0.50
     Blatt
    -0.50
     vulgaires
    -0.50
    WaitGroup
    -0.50
    POSITIVE LOGITS
     wireType
    0.82
    ientôt
    0.57
    XmlSchema
    0.52
     HasFactory
    0.51
    Населення
    0.50
     Biro
    0.50
    fromnode
    0.50
     <",
    0.49
    ברס
    0.48
     Préférences
    0.48
    Activations Density 0.642%

    No Known Activations