© 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. 14203
    Prev
    Next
    INDEX
    Explanations

    words that indicate a problem or challenge, especially in a research or technical context, or those that describe experiences and personal factors

    oai_token-act-pair · gemini-2.0-flash

    overcoming barriers

    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
     Barriers
    -1.87
     barrier
    -1.84
     barriers
    -1.84
    Barriers
    -1.80
     obstacle
    -1.77
     obstacles
    -1.73
     Barrier
    -1.72
    barrier
    -1.60
    Barrier
    -1.52
    obstacles
    -1.52
    POSITIVE LOGITS
     imp
    0.88
     Imp
    0.63
     STAND
    0.61
    imp
    0.57
     Stand
    0.56
     stand
    0.54
    Imp
    0.52
    STAND
    0.51
    Stand
    0.50
     modelAndView
    0.50
    Activations Density 1.360%

    No Known Activations