© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2446
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to software, operating systems like Ubuntu, and networking protocols.

    oai_token-act-pair · gemini-2.0-flash

    French chat conversations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     abbond
    -0.55
     alluminio
    -0.55
    ējās
    -0.54
     gră
    -0.53
     صوتيه
    -0.52
     profondeur
    -0.52
    ("}");
    -0.52
     priorité
    -0.51
    hemiah
    -0.51
    viesa
    -0.50
    POSITIVE LOGITS
    WebElementEntity
    0.66
    +:+
    0.53
    Chham
    0.49
    ftagPool
    0.49
     resourceCulture
    0.48
     kasarigan
    0.48
    لينكات
    0.46
    ConstraintMaker
    0.46
     بيها
    0.45
     للمعارف
    0.44
    Activations Density 0.828%

    No Known Activations