© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9831
    Prev
    Next
    INDEX
    Explanations

    URLs, the word "well", possessive contractions, and punctuation

    oai_token-act-pair · gemini-2.0-flash

    mixed content

    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
     Monfieur
    -0.90
     myſelf
    -0.90
     purpoſe
    -0.88
     themſelves
    -0.88
     himſelf
    -0.85
     cauſe
    -0.77
     Efq
    -0.76
     houſe
    -0.76
     becauſe
    -0.75
     Chriftian
    -0.74
    POSITIVE LOGITS
    des
    0.42
    Segoe
    0.42
     I
    0.41
    defn
    0.40
     Dr
    0.40
    AutoScaleMode
    0.40
    RefNanny
    0.40
    c
    0.39
    verifyException
    0.39
    zość
    0.38
    Activations Density 0.409%

    No Known Activations