© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12858
    Prev
    Next
    INDEX
    Explanations

    snippets of code with numbers, particularly those involved in parsing data or relating to "charge" and "state".

    oai_token-act-pair · gemini-2.0-flash

    state number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    TacToe
    -0.74
    tagHelperRunner
    -0.58
     Paglinawan
    -0.53
    SequentialGroup
    -0.52
    Geplaatst
    -0.52
    antine
    -0.50
    XmlType
    -0.49
    γων
    -0.48
     actionMode
    -0.47
     Roskov
    -0.46
    POSITIVE LOGITS
    SpringRunner
    0.62
    ChildScrollView
    0.59
    __(/*!
    0.57
    日閲覧
    0.56
    closedir
    0.56
    interopRequire
    0.54
     Familienname
    0.54
     Label
    0.53
     iload
    0.53
    存于互联网档案馆
    0.52
    Activations Density 1.592%

    No Known Activations