© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3620
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the game Oblivion, specifically names of locations, factions, and gameplay elements.

    oai_token-act-pair · gemini-2.0-flash

    computer-related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    complexContent
    -0.91
     tartalomajánló
    -0.90
    >{@
    -0.88
     ExecuteAsync
    -0.71
    Aiheesta
    -0.66
     المعيارى
    -0.64
    hyrchwyd
    -0.63
     BoxDecoration
    -0.63
    enterOuterAlt
    -0.63
     mergeFrom
    -0.63
    POSITIVE LOGITS
    CompleteListener
    0.49
     xr
    0.40
     ufficiale
    0.40
     เค
    0.40
    leiding
    0.39
    MockMvc
    0.39
    fiddle
    0.39
    beginPath
    0.38
     uitgenodigd
    0.37
     Gaye
    0.36
    Activations Density 0.533%

    No Known Activations