© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5337
    Prev
    Next
    INDEX
    Explanations

    mentions of backup power

    oai_token-act-pair · gemini-2.0-flash

    terms related to backup power supplies

    np_token-act-pair-logits · gpt-4o-mini

    Backup/reserve

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Hozzáférés
    -0.53
     Eintrag
    -0.48
     estekak
    -0.46
     isolada
    -0.46
    Портали
    -0.46
    şiv
    -0.46
     Exacts
    -0.45
    UnsafeEnabled
    -0.45
     ícone
    -0.45
    чне
    -0.43
    POSITIVE LOGITS
     backup
    1.22
     reserve
    1.13
     back
    1.10
     backups
    1.05
    reserve
    1.02
     extra
    0.99
     Backup
    0.97
     spare
    0.96
     Reserve
    0.95
    backup
    0.95
    Activations Density 1.406%

    No Known Activations