© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8987
    Prev
    Next
    INDEX
    Explanations

    casino game ads and potentially conversational French

    oai_token-act-pair · gemini-2.0-flash

    foreign text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    fjspx
    -0.58
     سكانية
    -0.58
     for
    -0.54
    PerformLayout
    -0.51
     Chwiliwch
    -0.49
     дорогой
    -0.48
    illent
    -0.48
    RenderAtEndOf
    -0.45
     but
    -0.45
    MessageInfo
    -0.44
    POSITIVE LOGITS
    Бахар
    0.62
    FONTE
    0.53
    bootstrapcdn
    0.53
    ℉
    0.53
     uska
    0.53
    HostException
    0.51
    脚注の使い方
    0.51
    ÁRIO
    0.49
     Référence
    0.49
     bords
    0.49
    Activations Density 0.192%

    No Known Activations