© 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. 9543
    Prev
    Next
    INDEX
    Explanations

    mentions of purpose in life, as well as symbolic reminders of such.

    oai_token-act-pair · gemini-2.0-flash

    role

    np_max-act · gemini-2.0-flash
    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
     position
    -1.02
     process
    -1.01
     most
    -1.01
     time
    -1.00
     only
    -0.99
     way
    -0.98
     first
    -0.95
     date
    -0.95
     line
    -0.94
     turn
    -0.94
    POSITIVE LOGITS
    LookAnd
    1.23
    ThroughAttribute
    1.17
    RegressionTest
    1.16
     nakalista
    1.06
     surla
    1.05
    tagHelperRunner
    1.00
     <<<<<<<<<<<<<<
    0.98
    providedIn
    0.97
    AndEndTag
    0.97
    StoryboardSegue
    0.95
    Activations Density 4.744%

    No Known Activations