© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12476
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to positive values and progress such as kindness, gratitude, fairness and love, but also words related to a desire for a better world

    oai_token-act-pair · gemini-2.0-flash

    virtues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    LookAnd
    -0.66
    parsedMessage
    -0.56
    شهاد
    -0.52
    ;</
    -0.50
    getActiveSheet
    -0.49
    adaptiveStyles
    -0.47
     MessageBoxIcon
    -0.45
     honnête
    -0.45
    luck
    -0.45
     AppCompatTheme
    -0.44
    POSITIVE LOGITS
    بوابة
    0.69
     سكانية
    0.60
    WarningLevel
    0.59
     متحده
    0.58
     increasingly
    0.57
    ROIT
    0.57
     cons
    0.56
    DoubleQuotes
    0.56
     quantitatively
    0.54
     समीक्षाएं
    0.53
    Activations Density 11.817%

    No Known Activations