© 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. 9368
    Prev
    Next
    INDEX
    Explanations

    a mix of numbers, monetary values, political terms and common words like 'the'

    oai_token-act-pair · gemini-2.0-flash

    strange

    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
    ftagPool
    -0.61
     ComVisible
    -0.61
    WithIdentifier
    -0.58
    initWithFrame
    -0.53
    IndentedString
    -0.52
    textAppearance
    -0.50
     bulunabilir
    -0.48
    fromUtf
    -0.47
    httphttps
    -0.47
    owieck
    -0.47
    POSITIVE LOGITS
     odd
    2.89
    odd
    2.20
     Odd
    1.94
    Odd
    1.93
    ODD
    1.23
     strange
    0.94
     oddly
    0.89
    strange
    0.83
     weird
    0.79
    odds
    0.79
    Activations Density 3.429%

    No Known Activations