© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5180
    Prev
    Next
    INDEX
    Explanations

    words or short phrases expressing positive sentiment or opinions.

    oai_token-act-pair · gemini-2.0-flash

    Helpfulness

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    AndEndTag
    -0.81
    mybatisplus
    -0.65
    __":
    -0.63
    ktop
    -0.59
    存于互联网档案馆
    -0.59
     jsPsych
    -0.58
    RectangleBorder
    -0.57
    EndContext
    -0.55
    localctx
    -0.54
     nahilalakip
    -0.54
    POSITIVE LOGITS
     having
    1.62
    Having
    1.54
     Having
    1.54
    having
    1.46
     knowing
    1.29
     HAVING
    1.25
     Knowing
    1.13
    Knowing
    1.06
    knowing
    1.05
     being
    1.04
    Activations Density 2.279%

    No Known Activations