© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9671
    Prev
    Next
    INDEX
    Explanations

    words related to something changing

    oai_token-act-pair · gemini-2.0-flash

    adapt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     adapt
    -1.91
     Adap
    -1.86
     adapting
    -1.84
     adaptation
    -1.83
     adapted
    -1.78
    Adap
    -1.76
    adapt
    -1.74
     Adapt
    -1.70
     Adaptation
    -1.70
     adap
    -1.70
    POSITIVE LOGITS
     незавершена
    0.75
     CreateTagHelper
    0.74
    #+#
    0.67
     betweenstory
    0.66
    AndEndTag
    0.64
     Baillargeon
    0.64
    الحياه
    0.63
    ponses
    0.62
    LookAnd
    0.59
     ThemeData
    0.59
    Activations Density 25.801%

    No Known Activations