© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13636
    Prev
    Next
    INDEX
    Explanations

    emotional or evaluative language, in the context of sports commentary and social commentary

    oai_token-act-pair · gemini-2.0-flash

    negative remarks or questions

    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
     Mention
    -0.79
     Mentions
    -0.71
     references
    -0.71
     hints
    -0.67
     allusions
    -0.65
     References
    -0.64
     препратки
    -0.63
     allusion
    -0.63
     Hints
    -0.62
     comments
    -0.62
    POSITIVE LOGITS
     الحره
    0.68
    ोंने
    0.56
     CreateTagHelper
    0.55
    >//
    0.55
    RenderAtEndOf
    0.54
     فريبيس
    0.54
    IndentedString
    0.52
    ViewFeatures
    0.51
    ьаж
    0.50
    __(/*!
    0.49
    Activations Density 26.002%

    No Known Activations