© 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. 15493
    Prev
    Next
    INDEX
    Explanations

    text in all-caps, or email-related terms

    oai_token-act-pair · gemini-2.0-flash

    affirmative statements

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

    complete sentences/phrases

    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
     purpoſe
    -0.71
     IBRARY
    -0.65
     pleaſure
    -0.64
     BRARY
    -0.61
    PERTIES
    -0.60
     ſch
    -0.58
     PICTOGRAM
    -0.57
     CHECKBOX
    -0.56
     séparation
    -0.56
     Majefty
    -0.56
    POSITIVE LOGITS
     IT
    0.76
     AND
    0.76
    
    0.67
     IS
    0.65
     WITH
    0.61
     AT
    0.61
     IN
    0.60
    ControllerAdvice
    0.60
     AS
    0.60
     ON
    0.60
    Activations Density 3.430%

    No Known Activations