© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13660
    Prev
    Next
    INDEX
    Explanations

    code or pseudo-code

    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
    ide
    -0.51
     aimer
    -0.49
     Boh
    -0.47
    وند
    -0.46
    dor
    -0.46
     Formal
    -0.46
     Faul
    -0.46
    edar
    -0.45
     dica
    -0.45
    gespräch
    -0.45
    POSITIVE LOGITS
    hésite
    0.84
    UTERS
    0.81
     kasarigan
    0.81
     CURIAM
    0.77
    KommentareTeilen
    0.76
    $")
    0.76
    enderror
    0.75
     оригіналу
    0.71
    })*/
    0.70
    });*/
    0.68
    Activations Density 0.595%

    No Known Activations