© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4112
    Prev
    Next
    INDEX
    Explanations

    words and phrases expressing obligation, possibility, requirement, permission, or expectation

    oai_token-act-pair · gemini-2.0-flash

    say "to"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     I
    -0.59
    PropertyChanging
    -0.58
     im
    -0.54
     Im
    -0.51
     —
    -0.51
     a
    -0.51
    <bos>
    -0.51
     occur
    -0.50
     known
    -0.50
     A
    -0.50
    POSITIVE LOGITS
     itſelf
    1.23
     myſelf
    1.22
     raiſ
    1.15
     Monfieur
    1.05
     themſelves
    1.02
     Efq
    1.00
     Theſe
    0.95
     purpoſe
    0.95
     ſtate
    0.94
     ſeveral
    0.94
    Activations Density 2.803%

    No Known Activations