© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12160
    Prev
    Next
    INDEX
    Explanations

    content from a variety of sources, including code, logs, forum posts, and articles with tags, likely indicating the presence of multiple and varied file types or informational sources

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     series
    -0.45
     nek
    -0.41
     insan
    -0.41
    mutex
    -0.40
    MD
    -0.39
    ena
    -0.39
    randint
    -0.38
    mod
    -0.38
    ţii
    -0.38
    ap
    -0.37
    POSITIVE LOGITS
     itſelf
    1.01
     Monfieur
    0.97
     raiſ
    0.97
     ſte
    0.93
     ſtand
    0.90
     leſs
    0.90
     Eſ
    0.89
     Jefus
    0.88
     ſche
    0.88
     pleaſure
    0.87
    Activations Density 2.600%

    No Known Activations