© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2983
    Prev
    Next
    INDEX
    Explanations

    things that are currently "under way."

    oai_token-act-pair · gemini-2.0-flash

    words related to preparations and processes

    np_token-act-pair-logits · gpt-4o-mini

    under and/or way

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     betweenstory
    -0.66
     estimés
    -0.65
    ValueStyle
    -0.65
     Seeder
    -0.59
     Мексичка
    -0.58
     createSlice
    -0.57
     Malte
    -0.54
     nargin
    -0.54
    הערות
    -0.54
    قایناق‌لار
    -0.53
    POSITIVE LOGITS
     under
    1.20
     Under
    1.13
    under
    1.12
    Under
    1.05
     UNDER
    0.98
    UNDER
    0.93
     way
    0.79
    way
    0.78
     onder
    0.69
     underway
    0.67
    Activations Density 1.514%

    No Known Activations