© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13620
    Prev
    Next
    INDEX
    Explanations

    words that end in 'like', but also has other behaviors

    oai_token-act-pair · gemini-2.0-flash

    similar

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     ModelExpression
    -0.67
     الدولى
    -0.63
    curities
    -0.52
    tagext
    -0.52
    requestCode
    -0.52
    æus
    -0.51
    RegistryLite
    -0.50
    нительно
    -0.49
     casada
    -0.48
    dhury
    -0.47
    POSITIVE LOGITS
    like
    1.70
    LIKE
    1.34
     looking
    1.27
    Like
    1.27
     like
    1.19
    looking
    1.17
     Like
    1.13
     sounding
    1.09
    esque
    1.07
    artige
    1.03
    Activations Density 2.506%

    No Known Activations