© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10471
    Prev
    Next
    INDEX
    Explanations

    the conjunction "og" and words or partial words "join", "drum" and "som"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     som
    -0.60
     somatic
    -0.59
     <",
    -0.58
     utafitiHapana
    -0.56
     indifer
    -0.55
    som
    -0.53
     légales
    -0.53
    帖最后由
    -0.52
    σθαι
    -0.52
    crollView
    -0.51
    POSITIVE LOGITS
    <bos>
    0.86
    はじめに
    0.68
    /***/
    0.64
     selve
    0.58
     Tri
    0.57
     ship
    0.55
    awtextra
    0.54
    readLine
    0.54
     its
    0.53
     edge
    0.53
    Activations Density 1.555%

    No Known Activations