© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13104
    Prev
    Next
    INDEX
    Explanations

    the word "like" used as a simile or comparison

    oai_token-act-pair · gemini-2.0-flash

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     consultato
    -0.66
    +#+#
    -0.63
    Eloquent
    -0.55
     practice
    -0.49
    QPalette
    -0.48
     likes
    -0.48
     Pingback
    -0.47
     TextEditing
    -0.46
    IGraphics
    -0.45
    ț
    -0.44
    POSITIVE LOGITS
     Jefus
    0.85
     myſelf
    0.76
     raiſ
    0.75
     itſelf
    0.73
    лтемелер
    0.72
     Monfieur
    0.72
     becauſe
    0.70
    ValueStyle
    0.69
     whoſe
    0.69
     weihnachten
    0.67
    Activations Density 0.084%

    No Known Activations