© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15215
    Prev
    Next
    INDEX
    Explanations

    terms containing "geo," "immuno," "mini,", or the letters "do".

    oai_token-act-pair · gemini-2.0-flash

    small things, immuno stuff

    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
    ly
    -1.59
    に
    -1.40
    了
    -1.29
    nya
    -1.27
    ness
    -1.10
    men
    -1.04
    the
    -1.01
    mos
    -0.96
    ting
    -0.95
    d
    -0.93
    POSITIVE LOGITS
    StackNavigator
    0.34
    djangoproject
    0.33
    й
    0.29
     UnityEditor
    0.26
     PropertyChanged
    0.25
    วย
    0.25
     Chwiliwch
    0.24
    //~
    0.24
    NEX
    0.24
     createStore
    0.23
    Activations Density 9.470%

    No Known Activations