© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3360
    Prev
    Next
    INDEX
    Explanations

    words related to positive feelings and beliefs

    oai_token-act-pair · gemini-2.0-flash

    Positive personal qualities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     determined
    -0.93
     determination
    -0.86
     Determination
    -0.82
     Determined
    -0.79
     commitment
    -0.72
    determined
    -0.70
    determination
    -0.67
     determining
    -0.67
     determine
    -0.66
    Deter
    -0.65
    POSITIVE LOGITS
    يميديا
    0.66
    MigrationBuilder
    0.65
     Мексичка
    0.63
    }{*}{
    0.57
     SwitchCompat
    0.57
     createStore
    0.56
     Normdatei
    0.56
    }{*}{}
    0.55
    AccessorTable
    0.55
    EndContext
    0.54
    Activations Density 6.497%

    No Known Activations