© 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. 4674
    Prev
    Next
    INDEX
    Explanations

    the word "alone" or similar words, or words related to medical examinations and observations

    oai_token-act-pair · gemini-2.0-flash

    alone

    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
    OrNil
    -1.16
    tagHelperRunner
    -1.16
    MLLoader
    -1.15
    出版年
    -1.13
    WaitGroup
    -1.11
    AndEndTag
    -1.07
    __(/*!
    -1.02
    enumii
    -0.97
    UnusedPrivate
    -0.96
     MainAxisSize
    -0.95
    POSITIVE LOGITS
    <bos>
    0.98
     
    0.96
    '
    0.87
    ↵↵
    0.83
    The
    0.82
    ↵
    0.82
     The
    0.75
    A
    0.65
    1
    0.65
    ’
    0.63
    Activations Density 1.851%

    No Known Activations