© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8014
    Prev
    Next
    INDEX
    Explanations

    mentions of methods or procedures, often using the words "this", "the", or "a".

    oai_token-act-pair · gemini-2.0-flash

    technique

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ThroughAttribute
    -0.86
    httphttps
    -0.84
     frameworks
    -0.81
     initComponents
    -0.81
     Framework
    -0.79
     Frameworks
    -0.78
    RegressionTest
    -0.76
     Mechanisms
    -0.75
     Plattform
    -0.75
    framework
    -0.75
    POSITIVE LOGITS
    estors
    0.50
    Neighbors
    0.44
     addressing
    0.42
     refiri
    0.40
    ailles
    0.40
     st
    0.39
    hiki
    0.39
     sy
    0.39
     scale
    0.38
    ticamente
    0.37
    Activations Density 3.756%

    No Known Activations