© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11247
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to business deals and plans

    oai_token-act-pair · gemini-2.0-flash

    negotiations or film industry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    xtext
    -0.54
     pitching
    -0.49
     pitches
    -0.48
    encodeWith
    -0.46
    sent
    -0.46
    StoryboardSegue
    -0.45
     كومونز
    -0.45
    TREATMENT
    -0.44
    unconfirmed
    -0.44
    ánto
    -0.44
    POSITIVE LOGITS
     allez
    0.60
     defStyleAttr
    0.56
     defStyle
    0.55
    HandlerContext
    0.54
    MemoryWarning
    0.53
    CFS
    0.51
    uchos
    0.49
    점
    0.49
     Enjoy
    0.48
     للمعارف
    0.48
    Activations Density 5.757%

    No Known Activations