© 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. 6294
    Prev
    Next
    INDEX
    Explanations

    language of deference spoken to or about royalty

    oai_token-act-pair · gemini-2.0-flash

    formal/governmental context

    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
     Paus
    -0.59
    HasColumnType
    -0.53
    ruhe
    -0.50
    namentales
    -0.50
    mány
    -0.49
     Stable
    -0.48
     Ast
    -0.48
    kloped
    -0.48
    Història
    -0.48
     Unmarshal
    -0.48
    POSITIVE LOGITS
    expandindo
    0.54
    WebMethod
    0.54
    WebServlet
    0.52
    unkel
    0.51
    writeFieldEnd
    0.48
    Enlaces
    0.47
    rophore
    0.46
     referenties
    0.44
    turnstile
    0.43
    FieldBuilder
    0.43
    Activations Density 1.319%

    No Known Activations