© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4086
    Prev
    Next
    INDEX
    Explanations

    mentions of telephones, phone lines, or mobile devices

    oai_token-act-pair · gemini-2.0-flash

    phone

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     phone
    -1.98
     Phone
    -1.84
    phone
    -1.73
    Phone
    -1.72
     PHONE
    -1.70
    PHONE
    -1.55
     phones
    -1.52
     telefon
    -1.51
     telephone
    -1.47
     Phones
    -1.40
    POSITIVE LOGITS
    mobile
    0.68
     mobile
    0.67
     Mobile
    0.67
    Mobile
    0.66
     Mob
    0.58
    Mob
    0.55
    MOBILE
    0.52
     FM
    0.48
     MOBILE
    0.47
     mobility
    0.46
    Activations Density 2.974%

    No Known Activations