© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7924
    Prev
    Next
    INDEX
    Explanations

    words related to legal, medical ,technical and academic writing.

    oai_token-act-pair · gemini-2.0-flash

    future tense forms of 'will'

    np_token-act-pair-logits · gpt-4o-mini

    will

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     تضيفلها
    -0.86
    PreferredItem
    -0.79
     OnTrigger
    -0.72
    StructEnd
    -0.69
     betweenstory
    -0.68
    AnimationsModule
    -0.65
     Shaksp
    -0.64
     createContext
    -0.63
     WaitForSeconds
    -0.61
    Personendaten
    -0.61
    POSITIVE LOGITS
     will
    1.40
     WILL
    0.84
     akan
    0.82
     shall
    0.80
    will
    0.79
    會
    0.77
     Will
    0.76
     ће
    0.73
    Will
    0.72
     vil
    0.68
    Activations Density 1.394%

    No Known Activations