© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7419
    Prev
    Next
    INDEX
    Explanations

    numerical digits, sometimes next to words like "bit."

    oai_token-act-pair · gemini-2.0-flash

    seven

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    autorelease
    -0.73
     jäl
    -0.62
    scribers
    -0.57
    TargetException
    -0.55
    bouncycastle
    -0.54
    }{#
    -0.53
    geführten
    -0.52
    ChildScrollView
    -0.52
    NUMX
    -0.51
    RTLD
    -0.51
    POSITIVE LOGITS
    InlineData
    0.68
    principalTable
    0.65
     Deadly
    0.61
     quite
    0.57
    ствую
    0.54
    Quite
    0.53
     Quite
    0.53
     deadly
    0.52
    quite
    0.52
    Deadly
    0.52
    Activations Density 0.950%

    No Known Activations