© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12123
    Prev
    Next
    INDEX
    Explanations

    sensory details related to events occurring within a narrative.

    oai_token-act-pair · gemini-2.0-flash

    bringing things inside

    np_max-act · gemini-2.0-flash

    groceries and locations

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    StoryboardSegue
    -0.66
    Geplaatst
    -0.62
    Série
    -0.58
    GraphicsUnit
    -0.53
    utnik
    -0.51
    cit
    -0.50
    userdetails
    -0.50
    +:+
    -0.49
    
    -0.48
    Hentet
    -0.48
    POSITIVE LOGITS
     doInBackground
    0.69
    Obrázky
    0.65
    CloseOperation
    0.57
    Initializable
    0.56
     esboço
    0.56
    AddHtmlAttribute
    0.53
    Throws
    0.52
     torchvision
    0.50
     respectivamente
    0.50
     IBOutlet
    0.49
    Activations Density 0.853%

    No Known Activations