© 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. 10438
    Prev
    Next
    INDEX
    Explanations

    the word "like" and words asociated with feeling something, especially something negative

    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
     like
    -1.66
     Like
    -1.23
    Like
    -1.13
     LIKE
    -1.08
    like
    -1.06
    <bos>
    -0.94
    LIKE
    -0.85
     seperti
    -0.79
     zoals
    -0.67
     مثل
    -0.65
    POSITIVE LOGITS
    ScopeManager
    1.02
    abestanden
    0.95
    BeginContext
    0.89
     EconPapers
    0.86
    EndInit
    0.79
     فريبيس
    0.79
     EnglishChoose
    0.78
    DebuggerNonUser
    0.78
     informée
    0.76
     незавершена
    0.75
    Activations Density 1.225%

    No Known Activations