© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5492
    Prev
    Next
    INDEX
    Explanations

    the words "phone", "cell phone", and similar terms

    oai_token-act-pair · gemini-2.0-flash

    phone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    -2.75
    phone
    -2.47
     Phone
    -2.42
    Phone
    -2.31
     PHONE
    -2.27
    PHONE
    -2.08
     telephone
    -2.08
     phones
    -2.05
     telefoon
    -1.98
     teléfono
    -1.89
    POSITIVE LOGITS
    ionali
    0.47
    SubType
    0.44
    monary
    0.42
    ocarcinoma
    0.41
    ///</
    0.41
     @"/
    0.40
     sub
    0.40
    aleza
    0.40
    ghold
    0.39
     кӀош
    0.39
    Activations Density 0.251%

    No Known Activations