© 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. 13870
    Prev
    Next
    INDEX
    Explanations

    code snippets, possibly in a specific language

    oai_token-act-pair · gemini-2.0-flash

    letter "a"

    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
     la
    -1.15
    La
    -0.84
     La
    -0.79
    la
    -0.72
     LA
    -0.66
     eine
    -0.65
    تقاوى
    -0.61
     AssemblyCulture
    -0.60
    Personensuche
    -0.59
    AnimationsModule
    -0.59
    POSITIVE LOGITS
     a
    1.04
    曖昧さ回避
    0.73
    a
    0.58
     nakalista
    0.56
    FundMe
    0.55
    A
    0.54
    หวัด
    0.54
    buzo
    0.53
    ſelves
    0.52
    antaranya
    0.51
    Activations Density 1.151%

    No Known Activations