© 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. 11777
    Prev
    Next
    INDEX
    Explanations

    the number 197

    oai_token-act-pair · gemini-2.0-flash

    Equations and scattered text

    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
     صوتيه
    -0.50
    WebControls
    -0.49
    cuterie
    -0.48
    ayage
    -0.47
     hashCode
    -0.47
    mines
    -0.47
    clerview
    -0.46
     tass
    -0.45
    orex
    -0.44
    alyptus
    -0.44
    POSITIVE LOGITS
     Progressive
    0.58
    Rhestr
    0.57
    OGND
    0.56
    円
    0.55
     disambiguazione
    0.52
     oreilles
    0.52
     keselamatan
    0.52
     šķ
    0.51
     Economic
    0.50
     bēr
    0.49
    Activations Density 8.105%

    No Known Activations