© 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. 12032
    Prev
    Next
    INDEX
    Explanations

    questions beginning with "how", "are", or containing the word "so"

    oai_token-act-pair · gemini-2.0-flash

    many things

    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
     many
    -2.00
    many
    -1.99
    Many
    -1.74
     Many
    -1.70
     MANY
    -1.66
     muchos
    -1.64
     muitos
    -1.63
    MANY
    -1.61
     molti
    -1.52
     viele
    -1.52
    POSITIVE LOGITS
     ma
    0.45
     (@
    0.43
     san
    0.43
     sin
    0.43
    рам
    0.42
    stateProvider
    0.42
     mu
    0.40
    ingang
    0.39
    junit
    0.39
    теризу
    0.39
    Activations Density 1.712%

    No Known Activations