© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6920
    Prev
    Next
    INDEX
    Explanations

    technical specifications such as CPU speed and memory size.

    oai_token-act-pair · gemini-2.0-flash

    Computer memory specifications

    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
    ScopeManager
    -0.78
    TagHelper
    -0.73
    DeleteBehavior
    -0.62
     незавершена
    -0.61
     balconies
    -0.58
    extAlignment
    -0.58
    WriteBarrier
    -0.57
     chitar
    -0.55
     facie
    -0.54
    Abp
    -0.53
    POSITIVE LOGITS
    ;"></
    0.49
     ✭✭
    0.47
    EDEFAULT
    0.46
     ExecuteAsync
    0.46
    |}{$
    0.45
    }_{+
    0.43
     دیکھیے
    0.43
    elope
    0.39
    trade
    0.39
     rade
    0.39
    Activations Density 1.116%

    No Known Activations