© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8874
    Prev
    Next
    INDEX
    Explanations

    instances of the words "ideal" or "perfect."

    oai_token-act-pair · gemini-2.0-flash

    ideal, perfect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    iare
    -0.45
     follicles
    -0.40
     conse
    -0.40
     inver
    -0.40
     creditor
    -0.40
     orbits
    -0.39
    Rendering
    -0.39
    서
    -0.39
     outre
    -0.39
    Lähteet
    -0.39
    POSITIVE LOGITS
    UnknownFields
    0.93
    apimachinery
    0.83
     JAXBElement
    0.74
    pushFollow
    0.73
     autorytatywna
    0.73
    CloseOperation
    0.70
    ImageContext
    0.69
    aphthalene
    0.66
    NUMX
    0.65
    SourceChecksum
    0.65
    Activations Density 0.239%

    No Known Activations