© 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. 12988
    Prev
    Next
    INDEX
    Explanations

    lines of code and programming markup

    oai_token-act-pair · gemini-2.0-flash

    @

    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
     form
    -0.58
    form
    -0.57
     forms
    -0.49
    uxxxx
    -0.49
    ThroughAttribute
    -0.48
     Form
    -0.46
     ioutil
    -0.46
    Form
    -0.45
     proper
    -0.44
     manufacture
    -0.44
    POSITIVE LOGITS
    GEBURTSDATUM
    0.98
    MigrationBuilder
    0.75
    UnknownFieldSet
    0.73
     typelib
    0.70
     препратки
    0.68
     GenerationType
    0.68
     виправивши
    0.62
    ReusableCell
    0.61
     насељу
    0.60
    RTDA
    0.60
    Activations Density 1.050%

    No Known Activations