© 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. 13539
    Prev
    Next
    INDEX
    Explanations

    varied collection of verbs, often associated with actions or processes

    oai_token-act-pair · 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
    ings
    -1.00
    ers
    -0.93
    inge
    -0.89
    Ing
    -0.81
    ingly
    -0.79
     ing
    -0.79
    ERS
    -0.72
    Билгалдахарш
    -0.71
    inga
    -0.68
     autorytatywna
    -0.68
    POSITIVE LOGITS
    ypeł
    0.50
     damos
    0.49
     "..\..\
    0.48
    __*/
    0.46
    vább
    0.44
     PS
    0.43
    fjspx
    0.42
     đặt
    0.41
    Sever
    0.41
    ptime
    0.41
    Activations Density 1.672%

    No Known Activations