© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 312
    Prev
    Next
    INDEX
    Explanations

    hexadecimal memory addresses

    oai_token-act-pair · gemini-2.0-flash

    say "number 6"

    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
     Nine
    -1.11
     nine
    -1.09
     Fourteen
    -1.04
    Nine
    -1.02
     Eight
    -0.99
     eight
    -0.98
     fifteenth
    -0.98
    Eight
    -0.97
     Eleven
    -0.97
     seventeen
    -0.97
    POSITIVE LOGITS
    6
    0.70
     neutre
    0.44
    ก่
    0.43
     OnInit
    0.42
    Axios
    0.42
    hagy
    0.42
    VideoCapture
    0.41
     zari
    0.41
    weiler
    0.40
     tark
    0.40
    Activations Density 2.787%

    No Known Activations