© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14865
    Prev
    Next
    INDEX
    Explanations

    mentions of the first person, particularly "I" and "me".

    oai_token-act-pair · gemini-2.0-flash

    personal stories and conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     incidente
    -0.50
    orney
    -0.50
     me
    -0.50
     us
    -0.49
    heça
    -0.47
    rawDesc
    -0.45
    enteuer
    -0.45
     conven
    -0.44
     conmigo
    -0.44
     @"/
    -0.44
    POSITIVE LOGITS
     Autorizaciones
    0.66
     hereto
    0.60
    MockMvc
    0.59
    Portály
    0.58
    intios
    0.56
    ModelAdmin
    0.56
     navideño
    0.55
     Ababa
    0.54
    verwijspagina
    0.54
    ItemBackground
    0.52
    Activations Density 6.897%

    No Known Activations