© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4972
    Prev
    Next
    INDEX
    Explanations

    unclear, but it seems to be activating on Russian text, and mathematical equations within what looks like a research paper

    oai_token-act-pair · gemini-2.0-flash

    left

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    ագրություններ
    -0.73
    Personendaten
    -0.73
    SharedCtor
    -0.72
    sidemargin
    -0.68
    TestingModule
    -0.67
     kaarangay
    -0.66
    OGND
    -0.66
     AspNetCore
    -0.66
    orsese
    -0.66
     ligiloj
    -0.65
    POSITIVE LOGITS
     catch
    0.52
    atorze
    0.47
    #
    0.47
    Copia
    0.45
    pera
    0.45
     swallow
    0.45
     alle
    0.43
     te
    0.41
    bumptech
    0.41
     conf
    0.41
    Activations Density 0.672%

    No Known Activations