Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9584
    Prev
    Next
    INDEX
    Explanations

    content that is not text, such as whitespace, programming code or other special markup

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    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
    цездатний
    -0.40
    oredCriteria
    -0.38
     égard
    -0.37
    Mixtures
    -0.34
    amse
    -0.32
     Biôgrafia
    -0.30
    ngths
    -0.29
     centrif
    -0.29
    ther
    -0.29
    Creep
    -0.28
    POSITIVE LOGITS
    Ārējās
    0.81
    argout
    0.69
    Ligações
    0.69
    openzeppelin
    0.68
    bootstrapcdn
    0.68
     and
    0.67
     发表于
    0.66
    indd
    0.66
     الاطلاع
    0.64
    Tikang
    0.64
    Activations Density 0.945%

    No Known Activations