© 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. 14572
    Prev
    Next
    INDEX
    Explanations

    the word "cut" in the context of finance, budgets, or prices

    oai_token-act-pair · gemini-2.0-flash

    cut

    np_max-act · gemini-2.0-flash

    ▁cut

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     “
    -0.63
    gend
    -0.63
     cut
    -0.63
    gese
    -0.59
     _
    -0.59
     kur
    -0.59
     sub
    -0.59
     sé
    -0.58
     code
    -0.58
     불
    -0.57
    POSITIVE LOGITS
     myſelf
    0.87
     itſelf
    0.86
     ་་
    0.84
     tfsi
    0.81
     Jefus
    0.81
     ―――――
    0.81
     themſelves
    0.80
     photolibrary
    0.80
     Houſe
    0.79
     Diſ
    0.79
    Activations Density 0.469%

    No Known Activations