© 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. 14993
    Prev
    Next
    INDEX
    Explanations

    hyphenated words and words with apostrophes indicating possession or contraction.

    oai_token-act-pair · gemini-2.0-flash

    -

    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
    -
    -1.41
    æus
    -0.71
    BeginContext
    -0.69
    -...
    -0.63
     co
    -0.62
    ianum
    -0.60
     id
    -0.60
     sin
    -0.59
    ratulations
    -0.59
    picuous
    -0.59
    POSITIVE LOGITS
     itſelf
    0.89
     varandra
    0.65
    s
    0.64
     deschis
    0.60
     Chriftian
    0.59
     latine
    0.59
     igenom
    0.58
     stör
    0.58
    withstanding
    0.57
     pleaſure
    0.57
    Activations Density 4.681%

    No Known Activations