© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7282
    Prev
    Next
    INDEX
    Explanations

    words related to software subscriptions, with some false positives from other domains like insurance and finance.

    oai_token-act-pair · gemini-2.0-flash

    future purchasing decisions

    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
     архивлан
    -0.57
     ModelExpression
    -0.55
    tagext
    -0.55
     Waray
    -0.53
     snippetHide
    -0.52
    #+#
    -0.50
    awtextra
    -0.50
    andes
    -0.48
    期刊论文
    -0.48
    /***/
    -0.48
    POSITIVE LOGITS
     PLWABN
    0.65
     resourceCulture
    0.64
    دانشنامهٔ
    0.57
    TagMode
    0.55
    enterOuterAlt
    0.54
    friger
    0.52
     Swanson
    0.52
    dealloc
    0.52
    minecraftforge
    0.50
    UMENTS
    0.49
    Activations Density 2.500%

    No Known Activations