© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12170
    Prev
    Next
    INDEX
    Explanations

    the word "or" and the word "and", sometimes along with commas

    oai_token-act-pair · gemini-2.0-flash

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     EdgeInsets
    -0.59
     kuin
    -0.47
     scarpe
    -0.47
     an
    -0.46
    get
    -0.46
     a
    -0.46
     sondern
    -0.45
    olites
    -0.45
    datas
    -0.45
    max
    -0.44
    POSITIVE LOGITS
     Мексичка
    0.89
     Italijanski
    0.74
     itſelf
    0.72
    noinspection
    0.67
    endgroup
    0.67
    NUMX
    0.66
    :✨
    0.65
     poffible
    0.65
     ſame
    0.63
    esus
    0.63
    Activations Density 2.016%

    No Known Activations