© 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. 7215
    Prev
    Next
    INDEX
    Explanations

    the word "mother" and related terms

    oai_token-act-pair · gemini-2.0-flash

    references to 'Mother' or related terms

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

    mother

    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
    ymus
    -0.57
    ThemeOverlay
    -0.54
     تانيه
    -0.54
    +:+
    -0.52
    monary
    -0.49
    ardless
    -0.49
    +#+
    -0.48
    typeorm
    -0.48
    borderFill
    -0.48
    illaries
    -0.48
    POSITIVE LOGITS
     snippetHide
    0.60
    RuleContext
    0.56
    MessageOf
    0.54
     jsPsych
    0.52
    uitton
    0.51
     setLoading
    0.50
    Tembelea
    0.49
     IBOutlet
    0.49
     dessen
    0.48
    chiede
    0.47
    Activations Density 1.635%

    No Known Activations