© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9350
    Prev
    Next
    INDEX
    Explanations

    a mix of common short words and words related to scientific or formal writing

    oai_token-act-pair · gemini-2.0-flash

    decision-making and performance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     linkovi
    -0.64
    Autoritní
    -0.62
    Hentet
    -0.57
    },[])
    -0.50
     Италијани
    -0.50
    principalTable
    -0.49
     ').
    -0.49
     ]];
    -0.49
    willReturn
    -0.48
    CreateModel
    -0.47
    POSITIVE LOGITS
    sidemargin
    0.63
     CURIAM
    0.63
    blurRadius
    0.60
    ruptedException
    0.57
    ConstraintMaker
    0.50
    pushFollow
    0.50
    remes
    0.49
    EndContext
    0.49
    getMinutes
    0.49
    toise
    0.48
    Activations Density 30.555%

    No Known Activations