© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2938
    Prev
    Next
    INDEX
    Explanations

    words related to personality traits or personal intent

    oai_token-act-pair · gemini-2.0-flash

    words related to emotional expression

    np_token-act-pair-logits · gpt-4o-mini

    expressing feelings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    expandindo
    -0.78
     CreateTagHelper
    -0.77
    transQ
    -0.70
     صوتيه
    -0.64
    +#+#
    -0.61
     للمعارف
    -0.61
    DllImport
    -0.60
    UrlResolution
    -0.59
    principalColumn
    -0.59
     @"/
    -0.58
    POSITIVE LOGITS
     expression
    1.67
     express
    1.52
    expression
    1.48
     show
    1.45
     expressing
    1.41
     display
    1.38
     showing
    1.38
     Expression
    1.38
     expressed
    1.38
    Express
    1.37
    Activations Density 2.405%

    No Known Activations