© 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. 5144
    Prev
    Next
    INDEX
    Explanations

    words related to printing

    oai_token-act-pair · gemini-2.0-flash

    paper and images

    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
    LayoutPanel
    -0.72
    ftagPool
    -0.68
    TargetException
    -0.67
    LookAnd
    -0.61
    StoryboardSegue
    -0.60
    Papel
    -0.59
     Hadrian
    -0.59
     Emer
    -0.58
    paper
    -0.58
     Suez
    -0.57
    POSITIVE LOGITS
     pinulongan
    0.52
     '\\;'
    0.49
    transQ
    0.48
    Subjects
    0.46
    Rüyada
    0.44
     Ga
    0.43
    ]),
    0.42
    postIndex
    0.41
     AssemblyTitle
    0.41
    atier
    0.40
    Activations Density 1.701%

    No Known Activations