© 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. 5344
    Prev
    Next
    INDEX
    Explanations

    article titles within a publication

    oai_token-act-pair · gemini-2.0-flash

    informational texts

    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
    AfterClass
    -0.50
    interopRequire
    -0.49
    __()
    -0.47
    зайн
    -0.47
     eorum
    -0.46
    AuthProvider
    -0.46
    Downloading
    -0.43
     bekend
    -0.43
     ejus
    -0.42
     intermedia
    -0.42
    POSITIVE LOGITS
     Focus
    0.73
     متعلقه
    0.71
    RenderAtEndOf
    0.68
    Havolalar
    0.66
    aarrggbb
    0.65
     Alert
    0.65
    OGND
    0.65
    Focus
    0.64
     Tip
    0.64
     Connection
    0.63
    Activations Density 2.257%

    No Known Activations