© 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. 15104
    Prev
    Next
    INDEX
    Explanations

    numerical values related to code

    oai_token-act-pair · gemini-2.0-flash

    1

    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
     Dostupné
    -0.52
    Datuak
    -0.48
     boucles
    -0.47
     verá
    -0.46
    },(
    -0.45
    age
    -0.45
    },[])
    -0.45
    ítés
    -0.45
    ites
    -0.43
    FormTagHelper
    -0.43
    POSITIVE LOGITS
     Мексичка
    0.71
     EconPapers
    0.70
    cookieParser
    0.59
     تانيه
    0.58
    ništvo
    0.56
     DBNull
    0.56
    featureID
    0.56
     оригіналу
    0.55
    Eloquent
    0.55
     caddy
    0.53
    Activations Density 0.635%

    No Known Activations