© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2662
    Prev
    Next
    INDEX
    Explanations

    mentions of curfews in a place called "ari"

    oai_token-act-pair · 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
    出版年
    -0.76
    AndEndTag
    -0.73
    انجليز
    -0.73
     كومونز
    -0.68
    EDEFAULT
    -0.67
    parsedMessage
    -0.66
    IndentedString
    -0.65
     autorytatywna
    -0.63
    DataPropertyName
    -0.61
    @"
    -0.61
    POSITIVE LOGITS
     subject
    0.48
     ActionResult
    0.46
     mAdapter
    0.46
    subject
    0.43
     Live
    0.41
    Live
    0.41
     sujet
    0.41
    ậu
    0.40
    Downloads
    0.40
    配
    0.40
    Activations Density 3.985%

    No Known Activations