© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12396
    Prev
    Next
    INDEX
    Explanations

    past perfect tense verbs and also some future tenses, and also mentions of relationships.

    oai_token-act-pair · gemini-2.0-flash

    ever

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     always
    -0.90
    always
    -0.85
     Always
    -0.83
    Always
    -0.73
    styleType
    -0.60
     selalu
    -0.59
     quelcon
    -0.58
     всегда
    -0.56
    Geplaatst
    -0.54
     alltid
    -0.52
    POSITIVE LOGITS
     ever
    2.83
     Ever
    2.02
    Ever
    2.00
    ever
    1.97
     EVER
    1.95
    EVER
    1.80
     ooit
    1.14
     từng
    1.01
     every
    0.98
     pernah
    0.97
    Activations Density 2.970%

    No Known Activations