© 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. 5537
    Prev
    Next
    INDEX
    Explanations

    sentences that use numbers, measures or achievements

    oai_token-act-pair · gemini-2.0-flash

    accomplishment

    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
    aarrggbb
    -0.83
    DebuggerNonUser
    -0.70
    UnusedPrivate
    -0.69
    webElementXpaths
    -0.69
    #
    -0.68
    存于互联网档案馆
    -0.68
    WriteBarrier
    -0.67
    /**
    -0.63
    SBATCH
    -0.63
    AccessorTable
    -0.63
    POSITIVE LOGITS
     accomplishment
    1.52
     achievement
    1.51
     feat
    1.27
     accomplished
    1.27
     accomplish
    1.24
     achievements
    1.24
     accomplishments
    1.21
     accomplishing
    1.21
    achievement
    1.17
     Achievement
    1.13
    Activations Density 0.874%

    No Known Activations