© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14784
    Prev
    Next
    INDEX
    Explanations

    personal writing about experiences and reflections concerning children and motherhood.

    oai_token-act-pair · gemini-2.0-flash

    uncommon or specific terms

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

    online writing and personality

    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
    Not in Any Lists

    No Comments

    Negative Logits
    rsiniz
    -0.54
     mineures
    -0.50
     connus
    -0.49
    share
    -0.49
     Share
    -0.48
     obligé
    -0.47
    SHARE
    -0.47
    Share
    -0.47
    mael
    -0.46
     gegangen
    -0.46
    POSITIVE LOGITS
    verwijspagina
    0.67
    rungsseite
    0.60
    oa̍t
    0.60
    ConstraintMaker
    0.59
     simplicity
    0.59
    specialchars
    0.58
     personality
    0.57
     дописавши
    0.57
     ugl
    0.56
     Réponses
    0.56
    Activations Density 1.056%

    No Known Activations