© 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. 12832
    Prev
    Next
    INDEX
    Explanations

    the word "personality" and, to a lesser extent, the word "worry"

    oai_token-act-pair · gemini-2.0-flash

    personality

    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
     personality
    -0.69
    personality
    -0.61
    perity
    -0.61
     coals
    -0.59
    ousands
    -0.59
     personalities
    -0.58
     Personality
    -0.58
    pital
    -0.57
    hematical
    -0.56
    estars
    -0.55
    POSITIVE LOGITS
    <bos>
    1.88
    '
    0.70
    ’
    0.66
    таратура
    0.62
    évaluateur
    0.60
     Paglinawan
    0.57
    SPJ
    0.57
    JspWriter
    0.54
    yntaxException
    0.52
    vų
    0.52
    Activations Density 0.475%

    No Known Activations