© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10705
    Prev
    Next
    INDEX
    Explanations

    negative political ideas about illegal disclosures and their legal consequences

    oai_token-act-pair · gemini-2.0-flash

    holder

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    WithMany
    -0.65
    ArrowToggle
    -0.62
     JAXBElement
    -0.58
    Jereo
    -0.54
     CURIAM
    -0.54
    Rujukan
    -0.52
    WriteBarrier
    -0.51
    BeginContext
    -0.50
    Παραπομπές
    -0.48
     consultato
    -0.46
    POSITIVE LOGITS
     holders
    0.85
     holder
    0.81
     Holders
    0.81
    tvguidetime
    0.72
    DockStyle
    0.67
     Holder
    0.64
     pump
    0.64
     bear
    0.62
    pump
    0.62
    holder
    0.62
    Activations Density 1.586%

    No Known Activations