© 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. 14596
    Prev
    Next
    INDEX
    Explanations

    language suggesting that the subject is connected to something

    oai_token-act-pair · gemini-2.0-flash

    philosophy religion spirituality

    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
     philosophical
    -1.29
     philosoph
    -1.24
    philosop
    -1.16
    Filosof
    -1.14
     philosopher
    -1.13
     philosophers
    -1.12
     Filosof
    -1.09
     filosof
    -1.08
     Philosop
    -1.05
     philosophic
    -1.04
    POSITIVE LOGITS
    RenderAtEndOf
    0.76
    мені
    0.55
     الدولى
    0.53
     Ad
    0.48
    Im
    0.48
     Plot
    0.47
    istoitu
    0.47
     Einwilligung
    0.47
    testcase
    0.46
     región
    0.46
    Activations Density 1.341%

    No Known Activations