© 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. 12386
    Prev
    Next
    INDEX
    Explanations

    mentions of meta-analysis type studies, including the people performing them

    oai_token-act-pair · gemini-2.0-flash

    Analyses, reviews, editing

    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
    WebElementEntity
    -0.49
    CASCADE
    -0.47
     im
    -0.46
     noDo
    -0.46
     '\\;'
    -0.44
    ghold
    -0.43
     مک
    -0.43
    iculture
    -0.43
    umburg
    -0.42
    afficheront
    -0.41
    POSITIVE LOGITS
    OGND
    0.79
     Grüsse
    0.66
    seamnă
    0.65
    aarrggbb
    0.60
     Opiniones
    0.59
     sprüche
    0.58
     Chwiliwch
    0.58
    AnchorStyles
    0.58
    berdayakan
    0.57
     photolibrary
    0.57
    Activations Density 1.132%

    No Known Activations