© 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. 11943
    Prev
    Next
    INDEX
    Explanations

    sentences discussing scientific study results and known/unknown information

    oai_token-act-pair · gemini-2.0-flash

    knowledge, research

    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
    UnknownFieldSet
    -0.78
    AddTagHelper
    -0.71
    MemoryWarning
    -0.66
    tvguidetime
    -0.66
    WriteTagHelper
    -0.66
    Personensuche
    -0.65
     propOrder
    -0.65
     CanadaChoose
    -0.65
    featureID
    -0.65
     ویکی‌پدی
    -0.63
    POSITIVE LOGITS
    HostException
    0.43
     mít
    0.41
     hearings
    0.39
     hearing
    0.39
    Sitting
    0.39
    //
    0.38
    実装
    0.38
    çade
    0.37
    omeness
    0.37
     skip
    0.36
    Activations Density 2.335%

    No Known Activations