© 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. 7358
    Prev
    Next
    INDEX
    Explanations

    sentences where someone wishes or wants for something

    oai_token-act-pair · gemini-2.0-flash

    Expressing wishes/regrets

    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
     Grüße
    -0.57
    HasForeignKey
    -0.56
    EndContext
    -0.56
     înc
    -0.53
    IBOutlet
    -0.51
    ngdoc
    -0.50
    Personendaten
    -0.50
    AndEndTag
    -0.50
    IsPostBack
    -0.49
    bukkit
    -0.49
    POSITIVE LOGITS
    AddTagHelper
    0.75
    WebVitals
    0.53
    NIO
    0.53
     للاسماء
    0.52
    avax
    0.50
    wende
    0.50
     Hierro
    0.49
    chtung
    0.47
    yszcz
    0.47
     rendus
    0.46
    Activations Density 7.276%

    No Known Activations