© 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. 10107
    Prev
    Next
    INDEX
    Explanations

    the words "carry" (or variants) or "portion".

    oai_token-act-pair · gemini-2.0-flash

    transfer/applying

    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
    InSection
    -0.66
    arpa
    -0.59
     snippetHide
    -0.58
    wieder
    -0.58
     Normdatei
    -0.58
     ReactDOM
    -0.57
    testens
    -0.57
    WithFormat
    -0.57
    styleType
    -0.56
    LikeLike
    -0.55
    POSITIVE LOGITS
    <bos>
    2.17
    '
    0.73
    ink
    0.57
    The
    0.56
    ’
    0.54
    Un
    0.53
    b
    0.52
    _
    0.51
    \
    0.50
     Infórmanos
    0.49
    Activations Density 0.321%

    No Known Activations