© 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. 10230
    Prev
    Next
    INDEX
    Explanations

    evaluative language, often expressing political opinions, ethical judgements, or emotional responses.

    oai_token-act-pair · gemini-2.0-flash

    Variations of "M"

    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
    abestanden
    -0.52
     Савезне
    -0.51
    Hochspringen
    -0.50
     disponibilités
    -0.50
    IVEREF
    -0.47
    ibut
    -0.47
    AddTagHelper
    -0.47
    cydow
    -0.43
    DeleteBehavior
    -0.42
    anzia
    -0.41
    POSITIVE LOGITS
     MM
    1.12
    MM
    1.03
     Me
    1.00
     Ма
    0.99
    Ｍ
    0.95
     Mi
    0.95
     Min
    0.95
     Ma
    0.93
    Me
    0.93
     Mo
    0.93
    Activations Density 43.962%

    No Known Activations