© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4105
    Prev
    Next
    INDEX
    Explanations

    words and phrases in various languages relating to historical documents and people's names

    oai_token-act-pair · gemini-2.0-flash

    potentially code

    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
     виправивши
    -0.70
     AttributeSet
    -0.67
    RenderAtEndOf
    -0.66
    VersionUID
    -0.66
    middels
    -0.60
     Gatt
    -0.59
    存于互联网档案馆
    -0.59
     <<<<<<<<<<<<<<
    -0.56
     cuadrada
    -0.56
    PerformLayout
    -0.55
    POSITIVE LOGITS
     ad
    0.58
     per
    0.52
     al
    0.49
     a
    0.49
    tenths
    0.47
    THAN
    0.46
    otomy
    0.45
     nel
    0.45
     di
    0.44
     ai
    0.44
    Activations Density 0.271%

    No Known Activations