© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9614
    Prev
    Next
    INDEX
    Explanations

    negative present tense conjugations of the verb "to be"

    oai_token-act-pair · gemini-2.0-flash

    aren't

    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
    Autoritní
    -1.08
     виправивши
    -1.04
     صوتيه
    -0.98
     AssemblyCulture
    -0.97
     فريبيس
    -0.94
     autorytatywna
    -0.94
    Were
    -0.93
     وتسجيلات
    -0.91
    InjectAttribute
    -0.88
     disambiguazione
    -0.88
    POSITIVE LOGITS
     is
    0.91
     was
    0.84
     has
    0.75
     follows
    0.61
     does
    0.59
     appears
    0.58
     gets
    0.57
     happens
    0.57
     goes
    0.57
     becomes
    0.57
    Activations Density 1.190%

    No Known Activations