© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11561
    Prev
    Next
    INDEX
    Explanations

    expressions of negativity, concern, or warning

    oai_token-act-pair · gemini-2.0-flash

    negative experiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     createdBy
    -0.59
    ที่ยว
    -0.58
     purified
    -0.58
    ίδ
    -0.57
     eil
    -0.57
    قایناق‌لار
    -0.57
     дописавши
    -0.56
    aryti
    -0.55
     varieties
    -0.54
     Elsewhere
    -0.54
    POSITIVE LOGITS
    <bos>
    1.30
     ContentValues
    0.49
     newOwner
    0.48
    fortawesome
    0.48
    HasAnnotation
    0.46
    первых
    0.46
     råd
    0.46
     question
    0.45
    الإنجليزية
    0.45
    createClass
    0.45
    Activations Density 1.571%

    No Known Activations