© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6086
    Prev
    Next
    INDEX
    Explanations

    mentions of oaths, vows, or swearing, often religious, and the obligations and preparations required.

    oai_token-act-pair · gemini-2.0-flash

    Oaths and pledges

    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
     مشين
    -0.68
    UnitTesting
    -0.64
     ſeveral
    -0.63
     Efq
    -0.63
     Diſ
    -0.61
     Theſe
    -0.61
     morire
    -0.60
     Monfieur
    -0.59
    ̍t
    -0.59
     uſe
    -0.59
    POSITIVE LOGITS
     pledge
    1.30
     commitment
    1.21
     commitments
    1.17
     pledges
    1.12
     commit
    1.10
     pledging
    1.08
     pledged
    1.08
    commitment
    1.05
     Commit
    1.05
    commit
    1.02
    Activations Density 0.664%

    No Known Activations