© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5614
    Prev
    Next
    INDEX
    Explanations

    company descriptions

    oai_token-act-pair · gemini-2.0-flash

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    izr
    -0.67
     سكانية
    -0.60
     estimés
    -0.54
    WithIOException
    -0.53
    tanleria
    -0.51
     FontFamily
    -0.50
    BeginContext
    -0.50
    nologue
    -0.49
    RegressionTest
    -0.48
    >${
    -0.46
    POSITIVE LOGITS
     pitting
    0.57
     Polda
    0.54
     Theſe
    0.51
     SUA
    0.51
    寥
    0.51
    汰
    0.50
     &___
    0.49
    setBold
    0.49
     Houſe
    0.49
    setCustom
    0.49
    Activations Density 2.362%

    No Known Activations