© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6870
    Prev
    Next
    INDEX
    Explanations

    phrases related to the limitations of accomplishing something, whether financial or theoretical

    oai_token-act-pair · gemini-2.0-flash

    reach

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    HtmlAttribute
    -0.69
    Parcelize
    -0.65
    DebuggerStep
    -0.62
     crowd
    -0.59
    Crowd
    -0.59
    mapStateToProps
    -0.57
     سكانية
    -0.56
     crowds
    -0.55
    badlogic
    -0.54
    Hentet
    -0.54
    POSITIVE LOGITS
     reach
    1.39
     Reach
    1.32
    reach
    1.21
    Reach
    1.21
     reached
    1.09
     reachable
    1.07
     reaching
    1.05
     reaches
    1.05
    reaching
    0.97
    reached
    0.97
    Activations Density 0.580%

    No Known Activations