© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 575
    Prev
    Next
    INDEX
    Explanations

    words related to combat and/or destruction

    oai_token-act-pair · gemini-2.0-flash

    crashing or breaking

    np_max-act-logits · gemini-2.0-flash
    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
     nahilalakip
    -0.56
     الاطلاع
    -0.56
    ⓧ
    -0.52
    ImageContext
    -0.51
    opf
    -0.51
    sidemargin
    -0.50
     henvisninger
    -0.50
     مشين
    -0.49
    LikeLiked
    -0.49
    Hozzáférés
    -0.49
    POSITIVE LOGITS
     ashore
    0.64
     régal
    0.57
     câte
    0.57
     Wiktionnaire
    0.56
     bambou
    0.56
    ็จ
    0.55
     actionMode
    0.52
     marbre
    0.51
     foncé
    0.51
     abstrait
    0.51
    Activations Density 3.115%

    No Known Activations