© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10482
    Prev
    Next
    INDEX
    Explanations

    words and phrases that refer to rules and regulations

    oai_token-act-pair · gemini-2.0-flash

    permissions related to alcohol

    np_token-act-pair-logits · gpt-4o-mini

    allow

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     pleaſure
    -0.94
     &___
    -0.92
     purpoſe
    -0.88
     raiſ
    -0.84
     myſelf
    -0.82
     uſe
    -0.82
     Jefus
    -0.82
     kasarigan
    -0.79
     poffible
    -0.79
     ſtate
    -0.79
    POSITIVE LOGITS
     Allow
    2.22
     allow
    2.22
    Allow
    2.17
    allow
    2.08
     allowed
    2.08
     allowing
    2.00
     ALLOW
    1.93
     Allowing
    1.93
     allows
    1.92
     permitting
    1.83
    Activations Density 5.237%

    No Known Activations