© 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. 14971
    Prev
    Next
    INDEX
    Explanations

    references to location

    oai_token-act-pair · gemini-2.0-flash

    location or direction

    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
    ⓧ
    -0.64
    contentLoaded
    -0.64
     EconPapers
    -0.60
     насељу
    -0.59
    WindowEvent
    -0.56
    smithy
    -0.55
    !*\
    -0.53
    LayoutStyle
    -0.53
    JspWriter
    -0.53
     boks
    -0.53
    POSITIVE LOGITS
     planet
    0.64
     earth
    0.56
    thenReturn
    0.55
     Réponses
    0.54
     footing
    0.53
     verwijzen
    0.52
     island
    0.50
    #+#
    0.48
     continent
    0.48
     pedestal
    0.48
    Activations Density 1.331%

    No Known Activations