© 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. 10832
    Prev
    Next
    INDEX
    Explanations

    a variety of common words, possibly related to the flow of simple sentence structure, or maybe the presence of a casual tone.

    oai_token-act-pair · gemini-2.0-flash

    damage and force

    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
    ByIndex
    -0.53
    śmie
    -0.50
     LXX
    -0.47
    amitié
    -0.44
     grateful
    -0.44
    Ⅳ
    -0.44
    getIndex
    -0.44
    devším
    -0.43
     Koper
    -0.43
     ajan
    -0.42
    POSITIVE LOGITS
     Roskov
    0.88
    adaptiveStyles
    0.85
    MigrationBuilder
    0.82
    Diwedd
    0.78
    دانشنامهٔ
    0.68
     للمعارف
    0.66
    MessageTagHelper
    0.65
     distanciation
    0.63
     kasarigan
    0.63
     مشين
    0.60
    Activations Density 5.885%

    No Known Activations