© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5820
    Prev
    Next
    INDEX
    Explanations

    sentences describing a radial arm saw

    oai_token-act-pair · gemini-2.0-flash

    Cutting tools

    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
     intptr
    -0.66
     محفوظة
    -0.63
     Efq
    -0.62
    sunt
    -0.61
     digress
    -0.60
     ***!
    -0.60
    tanleria
    -0.59
    pæ
    -0.59
     getMin
    -0.59
     Theſe
    -0.59
    POSITIVE LOGITS
     belas
    0.43
    hk
    0.43
     bar
    0.42
     calendriers
    0.42
    #
    0.41
     remplacé
    0.40
     invokingState
    0.40
    Tr
    0.38
    bar
    0.38
     flesta
    0.38
    Activations Density 2.148%

    No Known Activations