© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13132
    Prev
    Next
    INDEX
    Explanations

    words and phrases about goals and objectives

    oai_token-act-pair · gemini-2.0-flash

    aim/goal/objective

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     goal
    -0.98
     aim
    -0.93
     objectives
    -0.92
     goals
    -0.90
     aims
    -0.89
    goal
    -0.86
     purpose
    -0.85
     Aim
    -0.84
    Aim
    -0.84
    GOAL
    -0.80
    POSITIVE LOGITS
     resourceCulture
    0.63
     parezca
    0.52
     incroy
    0.52
    orianCalendar
    0.51
    енча
    0.51
    tagHelperRunner
    0.50
     Baillargeon
    0.50
     INVENTION
    0.50
    ++];
    0.50
     dovuto
    0.49
    Activations Density 14.994%

    No Known Activations