© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15596
    Prev
    Next
    INDEX
    Explanations

    the word "mental" and words related to it such as "possible", and health and professional contexts, suggesting it identifies discussions about mental well-being, abilities, or limitations.

    oai_token-act-pair · gemini-2.0-flash

    mental

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -1.25
     a
    -1.14
      
    -1.11
    ↵↵
    -1.09
     I
    -1.08
     A
    -1.05
     (
    -1.04
    <eos>
    -1.01
     R
    -0.98
     E
    -0.98
    POSITIVE LOGITS
     Anſ
    1.90
     itſelf
    1.83
     Efq
    1.82
     Monfieur
    1.82
     Majefty
    1.76
     Reſ
    1.74
     Houſe
    1.70
     Theſe
    1.69
     myſelf
    1.66
     themſelves
    1.63
    Activations Density 4.844%

    No Known Activations