© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15895
    Prev
    Next
    INDEX
    Explanations

    references to environment, potentially as viewed from an outside perspective and references to crime

    oai_token-act-pair · gemini-2.0-flash

    outside

    np_max-act · gemini-2.0-flash

    outside

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ↵↵
    -0.55
     the
    -0.54
    <bos>
    -0.54
    ↵
    -0.54
     kokona
    -0.48
     non
    -0.44
    InjectAttribute
    -0.44
      
    -0.42
     
    -0.42
     a
    -0.42
    POSITIVE LOGITS
    ormon
    0.80
     cherchés
    0.80
     Bioaccumulative
    0.73
     Nuovo
    0.73
     GetEnumerator
    0.72
    rašymas
    0.69
    jiga
    0.69
     eene
    0.69
     Argonne
    0.69
     Etudes
    0.68
    Activations Density 1.384%

    No Known Activations