© 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. 1040
    Prev
    Next
    INDEX
    Explanations

    the word "it" followed by "'s" or "was" within the same token

    oai_token-act-pair · gemini-2.0-flash

    It

    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
     ModelExpression
    -0.49
    RegressionTest
    -0.45
    Personendaten
    -0.45
    Espèce
    -0.44
    )}_
    -0.43
     Koy
    -0.43
    WSGI
    -0.42
     تضيفلها
    -0.42
     Esau
    -0.40
     Athene
    -0.40
    POSITIVE LOGITS
    Nuorodos
    0.65
    Viited
    0.65
    astify
    0.62
    Референце
    0.60
    OLIS
    0.58
    ching
    0.58
    maakt
    0.55
    woff
    0.55
     Does
    0.55
     transfieras
    0.55
    Activations Density 2.289%

    No Known Activations