© 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. 4947
    Prev
    Next
    INDEX
    Explanations

    words ending in '-ed' or '-ing' when they implicate someone in something, often with words related to dishonesty or deception

    oai_token-act-pair · gemini-2.0-flash

    deception, crime, or legal issues

    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
     doGet
    -0.60
     TSH
    -0.59
    arithmic
    -0.58
    UnknownFields
    -0.57
     bpy
    -0.56
    Palmar
    -0.55
     SqlConnection
    -0.54
    AWESOME
    -0.54
    ințe
    -0.54
     مشين
    -0.54
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.74
     us
    0.64
     me
    0.63
    
    0.59
    собенно
    0.57
    onAttach
    0.57
     informing
    0.56
     telling
    0.54
    __*/
    0.53
     informs
    0.52
    Activations Density 1.397%

    No Known Activations