© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16136
    Prev
    Next
    INDEX
    Explanations

    mentions of walls and pockets, occasionally also responding to "quirk" and the word "slightly"

    oai_token-act-pair · gemini-2.0-flash

    physical objects and locations

    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
     AÑO
    -0.58
     gloire
    -0.56
     religione
    -0.53
     TRABAJO
    -0.52
     sensuous
    -0.52
    y
    -0.52
    orianCalendar
    -0.51
    夠
    -0.50
    İK
    -0.50
     alphabetical
    -0.50
    POSITIVE LOGITS
    adaptiveStyles
    0.90
    :✨
    0.90
     Numerade
    0.85
     EconPapers
    0.82
    windowFixed
    0.81
     viewDidLoad
    0.73
    aarrggbb
    0.73
     Bioaccumulative
    0.68
     oprot
    0.66
     doInBackground
    0.66
    Activations Density 2.713%

    No Known Activations