© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10723
    Prev
    Next
    INDEX
    Explanations

    the words 'supposed' and 'gonna'

    oai_token-act-pair · gemini-2.0-flash

    intent or expectation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     تضيفلها
    -0.78
     препратки
    -0.77
    Portail
    -0.77
    RTLD
    -0.74
    rungsseite
    -0.74
     متعلقه
    -0.71
    tvguidetime
    -0.70
     ModelExpression
    -0.70
    Enllaces
    -0.70
    XmlAccessType
    -0.69
    POSITIVE LOGITS
    <bos>
    0.63
     to
    0.51
     čím
    0.49
     the
    0.47
    elseif
    0.46
    https
    0.43
     berhasil
    0.43
     https
    0.42
    ijnen
    0.42
    see
    0.42
    Activations Density 0.793%

    No Known Activations