© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11839
    Prev
    Next
    INDEX
    Explanations

    percentages and numbers related to statistics or school staff

    oai_token-act-pair · gemini-2.0-flash

    percentages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     şi
    -0.67
     favour
    -0.52
     optimise
    -0.51
     organising
    -0.51
     personalised
    -0.51
     favourable
    -0.51
     Şi
    -0.50
     authorised
    -0.50
     favoured
    -0.49
     minimise
    -0.49
    POSITIVE LOGITS
     ſtate
    0.85
     purpoſe
    0.84
     uſed
    0.79
     greateſt
    0.78
     themſelves
    0.77
     raiſ
    0.77
     pleaſure
    0.75
     poffible
    0.74
     tranſ
    0.74
     neceſſ
    0.74
    Activations Density 0.626%

    No Known Activations