© 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. 1566
    Prev
    Next
    INDEX
    Explanations

    what appears to be a mix of Russian characters and some sort of non-letter encoding

    oai_token-act-pair · gemini-2.0-flash

    Code, foreign language, noise

    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
     nationales
    -0.61
     fédé
    -0.59
    OptionsMenu
    -0.58
    Vegeu
    -0.56
    PostExecute
    -0.56
     Estadual
    -0.56
     createState
    -0.55
    Composição
    -0.54
     BoxDecoration
    -0.54
    ;;)
    -0.54
    POSITIVE LOGITS
    tifully
    0.45
     medesimo
    0.40
    емного
    0.36
    tréal
    0.35
     nôtre
    0.35
    ughty
    0.35
     mattino
    0.35
    hlmann
    0.35
    himura
    0.35
    remacy
    0.35
    Activations Density 0.188%

    No Known Activations