© 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. 13696
    Prev
    Next
    INDEX
    Explanations

    the letter "Y"

    oai_token-act-pair · gemini-2.0-flash

    y

    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
    Kaieteur
    -0.59
     iVar
    -0.58
    getItemId
    -0.53
     Waray
    -0.52
    quias
    -0.51
    OGND
    -0.51
    ঔ
    -0.50
    apeno
    -0.50
    NamedQueries
    -0.49
    itoral
    -0.48
    POSITIVE LOGITS
    tahankan
    0.57
    WriteTagHelper
    0.57
    AnchorStyles
    0.56
     démocr
    0.55
    ſelves
    0.52
     quæ
    0.51
    //});
    0.51
    ucca
    0.51
    usuf
    0.51
     pinulongan
    0.50
    Activations Density 2.160%

    No Known Activations