© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14141
    Prev
    Next
    INDEX
    Explanations

    measurements

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     ;
    -0.46
     seven
    -0.43
     :
    -0.42
    ;
    -0.41
    ()]
    -0.40
     Seven
    -0.39
     ge
    -0.38
     property
    -0.36
     Ve
    -0.36
     met
    -0.35
    POSITIVE LOGITS
     ainfi
    0.71
    XmlAccessorType
    0.70
     Theſe
    0.69
     HasFactory
    0.68
     Efq
    0.67
     internetowa
    0.67
     يتيمه
    0.66
     betweenstory
    0.65
     cdti
    0.65
     myſelf
    0.65
    Activations Density 5.739%

    No Known Activations