© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14997
    Prev
    Next
    INDEX
    Explanations

    references to social media and the word 'on'.

    oai_token-act-pair · gemini-2.0-flash

    social media mentions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     itſelf
    -0.95
     للمعارف
    -0.95
     postIndex
    -0.91
     myſelf
    -0.90
    ſelves
    -0.90
     themſelves
    -0.90
    ſelf
    -0.86
    tvguidetime
    -0.86
     himſelf
    -0.85
     snippetHide
    -0.84
    POSITIVE LOGITS
    InstanceState
    0.41
    loped
    0.40
    granate
    0.38
                                   
    0.35
    <eos>
    0.35
                                
    0.33
     digital
    0.33
    I
    0.33
     huellas
    0.32
    Á
    0.32
    Activations Density 0.560%

    No Known Activations