© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6313
    Prev
    Next
    INDEX
    Explanations

    references to socializing and friendship

    oai_token-act-pair · gemini-2.0-flash

    friends

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    IVEREF
    -0.64
     Trow
    -0.60
    DllImport
    -0.56
    resave
    -0.56
    :✨
    -0.56
    corder
    -0.55
    edel
    -0.54
    tholes
    -0.53
    TOL
    -0.53
    licious
    -0.53
    POSITIVE LOGITS
    enumi
    0.59
    脚注の使い方
    0.55
     Infórmanos
    0.53
    ाहरण
    0.53
     referenties
    0.53
     intptr
    0.51
     상세
    0.51
    further
    0.49
    ]),
    0.48
    ="@+
    0.48
    Activations Density 3.990%

    No Known Activations