© 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. 3611
    Prev
    Next
    INDEX
    Explanations

    the word "frequency"

    oai_token-act-pair · gemini-2.0-flash

    frequency

    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
    ensement
    -0.73
     ―――――
    -0.73
    audiovisuel
    -0.70
     $_"
    -0.69
     ―――
    -0.67
     ――――
    -0.66
     (\<
    -0.66
    .」
    -0.65
    ."),
    -0.64
    wollen
    -0.64
    POSITIVE LOGITS
    <bos>
    1.07
    LookAnd
    0.60
     оригіналу
    0.59
     the
    0.58
     tentativo
    0.56
     jöv
    0.56
     elé
    0.55
     gevol
    0.54
     مشين
    0.54
     érde
    0.53
    Activations Density 1.245%

    No Known Activations