© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10142
    Prev
    Next
    INDEX
    Explanations

    the word "behavior" and its variants

    oai_token-act-pair · gemini-2.0-flash

    behavior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     purpoſe
    -0.99
     pleaſure
    -0.86
    ſelf
    -0.84
     ſtre
    -0.84
     cauſe
    -0.84
     juſ
    -0.83
     ſtate
    -0.83
     Reſ
    -0.83
     ſta
    -0.82
     deſt
    -0.82
    POSITIVE LOGITS
    copg
    0.71
    reactstrap
    0.63
    <bos>
    0.63
    localVar
    0.61
    endmodule
    0.60
    cshtml
    0.59
    TagHelper
    0.57
    aspectj
    0.57
    migrationBuilder
    0.57
    पया
    0.57
    Activations Density 1.455%

    No Known Activations