© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12336
    Prev
    Next
    INDEX
    Explanations

    the word "inner" and other words that have a similar meaning to "internal" or opposite meaning to "outer."

    oai_token-act-pair · gemini-2.0-flash

    inner

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Theſe
    -0.69
     pardoned
    -0.66
     itſelf
    -0.65
     NDEBUG
    -0.65
     plais
    -0.64
     becauſe
    -0.62
    stości
    -0.62
     Jefus
    -0.61
     Suivez
    -0.61
    matitis
    -0.61
    POSITIVE LOGITS
    SequentialGroup
    0.89
     resourceCulture
    0.69
     "..\..\..\
    0.69
    ores
    0.68
    :].
    0.65
    (‘
    0.64
    rungsseite
    0.62
    ״
    0.60
    IntoConstraints
    0.59
    MFC
    0.59
    Activations Density 1.148%

    No Known Activations