© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6923
    Prev
    Next
    INDEX
    Explanations

    uses of "will" and "to" expressing intention, particularly regarding fixing mistakes, attempts, and future plans

    oai_token-act-pair · gemini-2.0-flash

    should

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    TargetApi
    -0.69
    WebElementEntity
    -0.64
    GenerationType
    -0.57
     متعلقه
    -0.50
    TabIndex
    -0.45
    Geplaatst
    -0.43
    ImageContext
    -0.43
     JAMA
    -0.43
     CUP
    -0.42
    addGap
    -0.42
    POSITIVE LOGITS
     betweenstory
    0.70
     Anſ
    0.65
     agrí
    0.57
     redeem
    0.56
    ьаж
    0.54
    tadır
    0.53
     kaarangay
    0.53
     lenker
    0.53
     utafitiHapana
    0.52
    MessageState
    0.52
    Activations Density 1.953%

    No Known Activations