© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14929
    Prev
    Next
    INDEX
    Explanations

    the end of code blocks or math formulas, or figure captions

    oai_token-act-pair · gemini-2.0-flash

    Math symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     to
    -0.77
     a
    -0.63
     no
    -0.60
     the
    -0.60
     an
    -0.59
     of
    -0.59
     long
    -0.58
     von
    -0.57
     is
    -0.56
     as
    -0.56
    POSITIVE LOGITS
     jsPsych
    0.86
     itſelf
    0.84
     quæ
    0.83
     Efq
    0.83
     greateſt
    0.82
    SceneManagement
    0.81
    taxia
    0.78
    Tikang
    0.77
     anún
    0.76
    esgue
    0.75
    Activations Density 2.147%

    No Known Activations