© 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. 10263
    Prev
    Next
    INDEX
    Explanations

    references to sources or reviews

    oai_token-act-pair · gemini-2.0-flash

    article text

    np_max-act · 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
    GraphicsUnit
    -0.90
    forRoot
    -0.88
     oleh
    -0.83
    Scénario
    -0.78
    AndEndTag
    -0.73
    SBATCH
    -0.70
    }`).
    -0.70
    ↹
    -0.69
    — 
    -0.69
     by
    -0.68
    POSITIVE LOGITS
     Clients
    0.42
    şan
    0.41
     Ens
    0.40
    her
    0.40
    Client
    0.39
    伝
    0.38
    Aux
    0.37
     Client
    0.37
     Cliente
    0.37
    chymal
    0.37
    Activations Density 0.673%

    No Known Activations