© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12192
    Prev
    Next
    INDEX
    Explanations

    words and phrases that describe opinions or judgments

    oai_token-act-pair · gemini-2.0-flash

    Achievement and overcoming challenges

    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
     Надо
    -0.72
     daß
    -0.65
     weitgehend
    -0.62
    )))),
    -0.61
     (;;)
    -0.61
     ?',
    -0.60
     надо
    -0.60
     läßt
    -0.59
     muß
    -0.57
     interposed
    -0.56
    POSITIVE LOGITS
     onCreateView
    0.68
    Kjelder
    0.68
    Alright
    0.67
     incredible
    0.66
    Additionally
    0.64
     incredibly
    0.63
     Additionally
    0.61
    除此之外
    0.61
    Anyways
    0.60
     recieve
    0.60
    Activations Density 2.431%

    No Known Activations