© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12387
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "problem", and sometimes "solution" if it's closely associated.

    oai_token-act-pair · gemini-2.0-flash

    problem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    problem
    -1.14
     problem
    -1.11
     Problem
    -1.07
    Problem
    -1.06
     PROBLEM
    -1.01
    PROBLEM
    -0.69
    createCanvas
    -0.69
    NOPQRST
    -0.69
     CURIAM
    -0.69
    SPATH
    -0.67
    POSITIVE LOGITS
     issues
    0.85
     Issues
    0.77
    issues
    0.72
    Issues
    0.68
    IBOutlet
    0.60
     ISSUES
    0.57
     issue
    0.56
    ISSUES
    0.55
    Välislingid
    0.52
    ībā
    0.49
    Activations Density 0.369%

    No Known Activations