© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14971
    Prev
    Next
    INDEX
    Explanations

    Java or C++ code and annotations

    oai_token-act-pair · gemini-2.0-flash

    getInstance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     препратки
    -0.66
     personale
    -0.66
    artige
    -0.64
    öglichkeiten
    -0.63
    SourceChecksum
    -0.62
     garg
    -0.60
    aderas
    -0.60
     Numerade
    -0.59
    \{\\
    -0.58
    matchCondition
    -0.55
    POSITIVE LOGITS
     GenerationType
    0.45
    __':
    0.42
    الحياه
    0.41
    farwyddwr
    0.41
    klaim
    0.40
    DeleteMapping
    0.40
    HideInInspector
    0.38
     Kompon
    0.37
    ћа
    0.37
     preocup
    0.37
    Activations Density 2.196%

    No Known Activations