© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5377
    Prev
    Next
    INDEX
    Explanations

    what appears to be non-English words or word fragments, potentially from various languages

    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
    rungsseite
    -0.47
     crdi
    -0.44
    RectangleBorder
    -0.44
     CM
    -0.42
     priori
    -0.41
     CME
    -0.41
    }$​
    -0.41
    ymmetric
    -0.40
     Wikimédia
    -0.40
    ječ
    -0.40
    POSITIVE LOGITS
     and
    0.71
    FieldDescriptor
    0.67
     BorderRadius
    0.67
    windowFixed
    0.64
    tvguidetime
    0.62
     FontFamily
    0.59
    DebuggerStep
    0.59
    RegressionTest
    0.58
    intéress
    0.58
     lezioni
    0.57
    Activations Density 0.261%

    No Known Activations