© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6405
    Prev
    Next
    INDEX
    Explanations

    instances of breaking from or with something and related contextual words

    oai_token-act-pair · gemini-2.0-flash

    break

    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
    EDEFAULT
    -0.55
     vieilles
    -0.50
     kvä
    -0.50
     säll
    -0.46
    NewUrlParser
    -0.45
    rativa
    -0.45
     préférence
    -0.45
     ordres
    -0.45
    Inflater
    -0.45
     håll
    -0.44
    POSITIVE LOGITS
    WebElementEntity
    0.69
    RectangleBorder
    0.68
    出版年
    0.61
    Hozzáférés
    0.59
    sizeCache
    0.57
    万美元
    0.55
     Rasulullah
    0.54
    ContentAsync
    0.52
     outcome
    0.52
    комиться
    0.52
    Activations Density 21.102%

    No Known Activations