© 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. 5750
    Prev
    Next
    INDEX
    Explanations

    something the analyzer is very unsure about, as it matches many different things with very low activation values

    oai_token-act-pair · gemini-2.0-flash

    by

    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
     Molecules
    -0.53
     object
    -0.52
    ్య
    -0.52
    OGND
    -0.52
    Objects
    -0.51
    IVEREF
    -0.51
    BindView
    -0.50
    UserScript
    -0.50
     objects
    -0.50
     protoimpl
    -0.49
    POSITIVE LOGITS
    ГЛА
    0.55
    DataAnnotations
    0.54
     Theſe
    0.54
    inafter
    0.54
     समीक्षक
    0.53
    っこう
    0.51
    verständlich
    0.51
    styleable
    0.50
     photolibrary
    0.50
    httphttps
    0.49
    Activations Density 3.712%

    No Known Activations