© 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. 9798
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating disagreement.

    oai_token-act-pair · gemini-2.0-flash

    say "words ending in ſelf"

    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
    1
    -0.54
    <eos>
    -0.52
    2
    -0.51
    5
    -0.49
    l
    -0.47
    <strong>
    -0.45
    0
    -0.45
    3
    -0.45
    4
    -0.44
    I
    -0.43
    POSITIVE LOGITS
     Efq
    1.46
     itſelf
    1.45
     myſelf
    1.41
     himſelf
    1.41
     Jefus
    1.41
     themſelves
    1.39
    ſelf
    1.38
     ſhe
    1.36
    ſelves
    1.25
     purpoſe
    1.25
    Activations Density 18.698%

    No Known Activations