© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4288
    Prev
    Next
    INDEX
    Explanations

    lines of code which include an object followed by a period

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    quinone
    -0.48
    otriva
    -0.47
    TRIBUN
    -0.46
    wikkeld
    -0.46
    glUniform
    -0.46
    clase
    -0.45
    postgresql
    -0.45
    inghouse
    -0.44
     Keys
    -0.44
     Hill
    -0.44
    POSITIVE LOGITS
    SharedCtor
    0.79
    tagHelperRunner
    0.66
     Theſe
    0.64
     ſche
    0.62
    MigrationBuilder
    0.59
     lenker
    0.58
     Eſ
    0.57
     itſelf
    0.57
    .[/
    0.57
     theſe
    0.57
    Activations Density 1.335%

    No Known Activations