© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14252
    Prev
    Next
    INDEX
    Explanations

    mentions of color spaces and image processing, as well as the NFC East sports division and medical terminology related to childbirth

    oai_token-act-pair · gemini-2.0-flash

    HSV

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    BufferException
    -0.69
    principalTable
    -0.66
    Geplaatst
    -0.66
    MethodManager
    -0.66
     déclen
    -0.63
     BoxFit
    -0.62
     referenties
    -0.59
    Enllaços
    -0.59
     Chwiliwch
    -0.59
     muualla
    -0.58
    POSITIVE LOGITS
    _));
    0.66
     MenuView
    0.59
     triad
    0.49
     four
    0.48
    ArrowToggle
    0.48
    MIDDLEWARE
    0.47
    four
    0.47
    Four
    0.47
     carried
    0.45
     trio
    0.45
    Activations Density 2.783%

    No Known Activations