© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5136
    Prev
    Next
    INDEX
    Explanations

    the word "themselves" and related words

    oai_token-act-pair · gemini-2.0-flash

    themselves

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     cielos
    -0.83
     виправивши
    -0.75
     élas
    -0.66
     mijne
    -0.63
     envers
    -0.62
    ówczas
    -0.62
     impianti
    -0.61
     ospiti
    -0.61
     magasins
    -0.61
     imprensa
    -0.60
    POSITIVE LOGITS
    ValueStyle
    0.66
     expected
    0.65
     lda
    0.63
    TagMode
    0.60
    rativa
    0.60
    ablanca
    0.58
     araw
    0.58
    mány
    0.58
     asper
    0.57
    іга
    0.57
    Activations Density 1.896%

    No Known Activations