© 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. 3545
    Prev
    Next
    INDEX
    Explanations

    sentences containing auxiliary verbs of advisement or necessity

    oai_token-act-pair · gemini-2.0-flash

    should

    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
     itſelf
    -3.98
     myſelf
    -3.97
     pleaſure
    -3.95
     Monfieur
    -3.95
     ſche
    -3.89
     purpoſe
    -3.81
     Majefty
    -3.72
     raiſ
    -3.59
     ſtate
    -3.58
     Shakspeare
    -3.58
    POSITIVE LOGITS
     
    2.14
     “
    2.02
     a
    1.96
     ‘
    1.96
     "
    1.91
     an
    1.86
     I
    1.84
     la
    1.84
     qu
    1.80
     de
    1.80
    Activations Density 5.828%

    No Known Activations