© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11201
    Prev
    Next
    INDEX
    Explanations

    words related to phone calls and contracts

    oai_token-act-pair · gemini-2.0-flash

    Telephone

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ništ
    -0.54
    Hochspringen
    -0.51
    utación
    -0.50
     Walsh
    -0.47
    esser
    -0.47
    achal
    -0.45
     Stopped
    -0.45
    IDADE
    -0.45
     address
    -0.44
    kura
    -0.44
    POSITIVE LOGITS
    expandindo
    0.87
     дописавши
    0.66
    VIAF
    0.64
    الحياه
    0.62
     betweenstory
    0.62
     collect
    0.61
     يتيمه
    0.60
    LookAnd
    0.60
     getopt
    0.59
     مشين
    0.58
    Activations Density 2.115%

    No Known Activations