© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8470
    Prev
    Next
    INDEX
    Explanations

    programming code snippets, especially in languages used for app development

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     Мексичка
    -0.66
     ModelExpression
    -0.60
    DebuggerNonUser
    -0.56
    wohnt
    -0.56
     imper
    -0.56
    shots
    -0.54
     Responding
    -0.53
    continence
    -0.52
     Réponses
    -0.52
     ProtoMessage
    -0.51
    POSITIVE LOGITS
    MigrationBuilder
    0.60
     EconPapers
    0.57
    :✨
    0.53
    yargs
    0.51
     humaines
    0.51
    httphttps
    0.49
     citation
    0.48
     transfieras
    0.47
    skraft
    0.47
    יצד
    0.47
    Activations Density 0.515%

    No Known Activations