© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5357
    Prev
    Next
    INDEX
    Explanations

    words relating to scarcity and loss of resources

    oai_token-act-pair · gemini-2.0-flash

    left

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    AndEndTag
    -0.94
     MainAxisSize
    -0.75
    StoryboardSegue
    -0.61
    tdessen
    -0.60
    Cyfeiriadau
    -0.58
     дописавши
    -0.57
     متعلقه
    -0.56
    دانشنامهٔ
    -0.54
    ImageContext
    -0.52
     때문
    -0.51
    POSITIVE LOGITS
     left
    2.84
    left
    2.19
     Left
    2.16
    Left
    2.11
     LEFT
    2.06
    LEFT
    1.75
    左
    1.60
     izquierda
    1.46
     左
    1.34
     sinistra
    1.34
    Activations Density 11.590%

    No Known Activations