© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14618
    Prev
    Next
    INDEX
    Explanations

    the word "transition"

    oai_token-act-pair · gemini-2.0-flash

    transition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Мексичка
    -1.11
     Савезне
    -1.11
    Personendaten
    -1.09
    findpost
    -1.08
    MethodManager
    -1.07
     Вікіпе
    -1.05
    iffion
    -1.02
     defaultstate
    -1.00
    InjectAttribute
    -0.99
    +:+
    -0.97
    POSITIVE LOGITS
    A
    0.77
    1
    0.75
    a
    0.75
    2
    0.74
    I
    0.74
    3
    0.72
    5
    0.71
    0
    0.67
     
    0.65
    i
    0.65
    Activations Density 1.119%

    No Known Activations