© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5641
    Prev
    Next
    INDEX
    Explanations

    telephone and mail services

    oai_token-act-pair · gemini-2.0-flash

    instances of the word 'phone'

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

    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_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
     ويكيميديا
    -0.66
    abstractmethod
    -0.57
     فريبيس
    -0.57
    endphp
    -0.56
    তথ্যসূত্র
    -0.56
     otomatig
    -0.55
     useStyles
    -0.50
    kadot
    -0.49
     समीक्षाओं
    -0.49
    PMailer
    -0.49
    POSITIVE LOGITS
    tvguidetime
    0.76
     BoxDecoration
    0.59
    FormTagHelper
    0.59
     LINES
    0.58
    WebElementEntity
    0.56
    YMMV
    0.54
     PIT
    0.53
     CreateTagHelper
    0.52
     Audiodateien
    0.52
     lines
    0.51
    Activations Density 1.143%

    No Known Activations