© 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. 13588
    Prev
    Next
    INDEX
    Explanations

    positive descriptions using the word "clear."

    oai_token-act-pair · gemini-2.0-flash

    clear

    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
     clear
    -3.17
    clear
    -2.78
     Clear
    -2.73
    Clear
    -2.64
     CLEAR
    -2.44
     clears
    -2.25
    CLEAR
    -2.19
     clearer
    -2.02
     clearing
    -1.88
     cleared
    -1.83
    POSITIVE LOGITS
     оригіналу
    0.73
    GEBURTSDATUM
    0.69
    styleType
    0.59
    abra
    0.56
    PreferredItem
    0.52
    tvguidetime
    0.51
     ffilmiau
    0.50
    StreetMap
    0.50
    InjectAttribute
    0.50
    GroupLayout
    0.49
    Activations Density 3.122%

    No Known Activations