© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 774
    Prev
    Next
    INDEX
    Explanations

    words with high sentiment toward an action or event, or verbs that show actions.

    oai_token-act-pair · 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
     He
    -2.47
    He
    -2.22
     His
    -1.48
    His
    -1.41
    he
    -1.32
     Он
    -1.27
     She
    -1.12
     Himself
    -1.12
     Him
    -1.02
     Він
    -1.02
    POSITIVE LOGITS
    stdc
    0.61
    AddTagHelper
    0.53
    etka
    0.52
     Efq
    0.51
     Anſ
    0.51
    >{@
    0.49
    gister
    0.48
     Wicidata
    0.48
    جغرافيا
    0.47
     _:
    0.47
    Activations Density 19.899%

    No Known Activations