© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8516
    Prev
    Next
    INDEX
    Explanations

    phrases that express disagreement, disbelief, or questioning of something.

    oai_token-act-pair · gemini-2.0-flash

    internet forum posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     WaitForSeconds
    -0.64
     marginLeft
    -0.60
     UIAlert
    -0.59
     malice
    -0.52
    istoitu
    -0.52
    leiding
    -0.52
     Vikipedi
    -0.52
     asunder
    -0.51
    ValueStyle
    -0.51
    PRWEB
    -0.50
    POSITIVE LOGITS
    
    0.49
     sekali
    0.48
     abgerufen
    0.46
    bukaan
    0.45
    věr
    0.45
    Set
    0.42
    ēju
    0.41
    íp
    0.41
    Aiheesta
    0.41
    cribir
    0.41
    Activations Density 0.494%

    No Known Activations