© 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. 8702
    Prev
    Next
    INDEX
    Explanations

    common short words such as prepositions and articles.

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    AndEndTag
    -0.65
     sayap
    -0.54
     مشين
    -0.52
    ścio
    -0.51
    AddressBook
    -0.50
     namelijk
    -0.49
    titleMargin
    -0.49
     calendriers
    -0.49
    ')):
    -0.48
    sedia
    -0.48
    POSITIVE LOGITS
    /**
    0.59
    ioutil
    0.57
    GroupLayout
    0.57
    DOCTYPE
    0.56
     endblock
    0.55
    #+#
    0.54
    最快更新
    0.54
    mbar
    0.52
    XmlAccessorType
    0.52
    PasswordEncoder
    0.51
    Activations Density 7.301%

    No Known Activations