© 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. 12056
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases involving both technology companies and people

    oai_token-act-pair · gemini-2.0-flash

    that

    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
    :✨
    -0.73
    órum
    -0.61
     direct
    -0.60
    onAttach
    -0.60
    ⓘ
    -0.59
     skew
    -0.58
     Groom
    -0.57
     disambiguazione
    -0.57
     dilute
    -0.56
     testSet
    -0.56
    POSITIVE LOGITS
     un
    0.98
     Un
    0.70
    Un
    0.68
    OGND
    0.68
    un
    0.66
     unha
    0.64
     une
    0.61
     UN
    0.52
    jgl
    0.49
    乓
    0.48
    Activations Density 0.896%

    No Known Activations