© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5464
    Prev
    Next
    INDEX
    Explanations

    different forms of the word 'agree'

    oai_token-act-pair · gemini-2.0-flash

    agree

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     agree
    -1.73
     agreed
    -1.63
     agrees
    -1.39
    Agreed
    -1.27
     Agree
    -1.21
     agreeing
    -1.20
    agreed
    -1.16
     Agreed
    -1.16
    agree
    -1.16
    Agree
    -1.13
    POSITIVE LOGITS
    InjectAttribute
    0.94
     صوتيه
    0.87
     يتيمه
    0.82
     nakalista
    0.81
     Theſe
    0.80
     Monfieur
    0.79
     EnglishChoose
    0.77
    InSection
    0.76
     snippetHide
    0.76
     pseudonym
    0.75
    Activations Density 0.472%

    No Known Activations