© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12522
    Prev
    Next
    INDEX
    Explanations

    mentions of one person touching another person's arm, hand, or fingertips

    oai_token-act-pair · gemini-2.0-flash

    hand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    UnsafeEnabled
    -0.71
     doubtnut
    -0.70
     myſelf
    -0.68
     Normdatei
    -0.65
    SharedDtor
    -0.63
     Савезне
    -0.63
     Houſe
    -0.62
    AnchorStyles
    -0.62
    Geplaatst
    -0.60
    expandindo
    -0.59
    POSITIVE LOGITS
    PhysRevD
    0.56
     uintptr
    0.47
    HomeAsUpEnabled
    0.46
    жде
    0.45
     دیکھیے
    0.44
    manni
    0.42
    henswürdigkeiten
    0.42
     AssemblyTitle
    0.41
     di
    0.41
    ünkü
    0.41
    Activations Density 0.576%

    No Known Activations