© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4980
    Prev
    Next
    INDEX
    Explanations

    the word "alternately" and words containing the "tern" and "at" token sequence

    oai_token-act-pair · gemini-2.0-flash

    ately

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Soccerway
    -0.69
    脚注の使い方
    -0.65
     生命周期
    -0.60
    Referències
    -0.56
    TagMode
    -0.55
    migrationBuilder
    -0.54
    клопе
    -0.53
    "?>
    -0.50
    Šaltiniai
    -0.50
    tserrat
    -0.49
    POSITIVE LOGITS
     alternative
    1.36
     ALTERN
    1.23
     Alternative
    1.23
    alternative
    1.22
     alternatives
    1.21
     Altern
    1.21
    Alternative
    1.17
    ALTERN
    1.16
    Altern
    1.16
     alternativ
    1.15
    Activations Density 0.590%

    No Known Activations