© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11070
    Prev
    Next
    INDEX
    Explanations

    parenthesized abbreviations and acronyms

    oai_token-act-pair · gemini-2.0-flash

    computer language

    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
     POM
    -0.95
     BAM
    -0.93
     SCM
    -0.93
     SAM
    -0.93
     PSM
    -0.92
     APM
    -0.91
     CCM
    -0.91
     RIM
    -0.91
     SPM
    -0.90
     TAM
    -0.90
    POSITIVE LOGITS
    twimg
    0.59
    principalTable
    0.59
     оригіналу
    0.58
    findpost
    0.53
    INCREF
    0.52
     typelib
    0.51
    RegistryLite
    0.50
    lorette
    0.49
     الرخصة
    0.48
     légales
    0.48
    Activations Density 1.157%

    No Known Activations