© 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. 6766
    Prev
    Next
    INDEX
    Explanations

    the word "save" and terms related to "saving"

    oai_token-act-pair · gemini-2.0-flash

    save

    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
     saving
    -3.05
     save
    -2.89
     saved
    -2.88
     saves
    -2.67
     Save
    -2.63
     Saving
    -2.63
    save
    -2.58
    Save
    -2.55
    Saving
    -2.50
    saving
    -2.48
    POSITIVE LOGITS
    脚注の使い方
    0.75
    enumi
    0.68
    Зноскі
    0.56
    Istorija
    0.53
    Lon
    0.52
     TextInputType
    0.52
    icitis
    0.51
     surla
    0.51
    ьаж
    0.50
    soi
    0.50
    Activations Density 0.855%

    No Known Activations