© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7705
    Prev
    Next
    INDEX
    Explanations

    the word "an" followed by a word

    oai_token-act-pair · gemini-2.0-flash

    an

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     i
    -0.37
     inflater
    -0.32
     ed
    -0.32
     électron
    -0.31
    oob
    -0.31
     oran
    -0.31
     el
    -0.30
    ther
    -0.30
     ['./
    -0.30
    nh
    -0.29
    POSITIVE LOGITS
     kasarigan
    1.22
    OGND
    1.09
    bootstrapcdn
    1.05
    تقاوى
    0.95
    AccessorTable
    0.93
    enterOuterAlt
    0.93
    ]")]
    0.92
     nahilalakip
    0.92
    WithIOException
    0.89
    GEBURTSDATUM
    0.88
    Activations Density 0.278%

    No Known Activations