© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6295
    Prev
    Next
    INDEX
    Explanations

    descriptions of objects with shaped parts that are supportive and conform to the shape of other objects

    oai_token-act-pair · gemini-2.0-flash

    that which

    np_max-act-logits · gemini-2.0-flash

    that/which

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    -1.00
     متعلقه
    -0.82
     NSCoder
    -0.70
     BoxDecoration
    -0.69
    SpringBootTest
    -0.68
    FormTagHelper
    -0.67
    ToBounds
    -0.66
    iastes
    -0.65
    IntoConstraints
    -0.65
    copal
    -0.63
    POSITIVE LOGITS
     pro
    0.54
     fills
    0.47
    eri
    0.46
     slides
    0.46
     választ
    0.45
     drops
    0.45
    pro
    0.44
     tap
    0.44
    ari
    0.44
     drop
    0.43
    Activations Density 4.332%

    No Known Activations