© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13534
    Prev
    Next
    INDEX
    Explanations

    instances of "we" or "you" followed by words like "have" and "to" that create a tone of motivation and offering advice

    oai_token-act-pair · gemini-2.0-flash

    advice and encouragement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    webElementXpaths
    -0.90
     CreateTagHelper
    -0.85
    WebElementEntity
    -0.79
    ContentAlignment
    -0.74
    Personendaten
    -0.73
    Vidite
    -0.73
    protoimpl
    -0.73
    MockBean
    -0.71
    ⟬
    -0.70
    DllImport
    -0.70
    POSITIVE LOGITS
     state
    0.50
    とも
    0.48
     Доро
    0.45
     jeunesse
    0.44
     un
    0.44
    letras
    0.43
     examine
    0.41
    tenham
    0.40
    框
    0.40
    tap
    0.40
    Activations Density 4.915%

    No Known Activations