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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3706
    Prev
    Next
    INDEX
    Explanations

    references to carrying bags

    oai_token-act-pair · gemini-2.0-flash

    bags

    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
     Bag
    -2.03
     bags
    -2.02
     bag
    -2.00
    Bag
    -1.98
    bag
    -1.94
     Bin
    -1.93
    bags
    -1.91
     Bags
    -1.88
     bin
    -1.86
     BAG
    -1.86
    POSITIVE LOGITS
     ThemeData
    0.54
     MotionEvent
    0.51
     فريبيس
    0.49
     Roskov
    0.47
     JpaRepository
    0.47
    vetica
    0.47
    ///</
    0.46
     CURIAM
    0.46
    MENTE
    0.45
    StoryboardSegue
    0.44
    Activations Density 1.797%

    No Known Activations