© 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. 13898
    Prev
    Next
    INDEX
    Explanations

    words that start with "gr" expressing negative sentiment

    oai_token-act-pair · gemini-2.0-flash

    the sequence "gr" in various forms

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

    say "Gr" words

    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
    ParallelGroup
    -0.59
     nhiên
    -0.55
    دانشنامهٔ
    -0.54
    deviantart
    -0.54
    httphttps
    -0.52
     Antilles
    -0.52
    OrNil
    -0.51
    argout
    -0.49
    __*/
    -0.48
    
    -0.48
    POSITIVE LOGITS
    ագրություններ
    0.63
    Dış
    0.57
     esternos
    0.55
     CreateTagHelper
    0.53
     relâche
    0.52
    věř
    0.52
     cec
    0.51
    issens
    0.50
     Wikimedijinoj
    0.47
    lež
    0.47
    Activations Density 0.254%

    No Known Activations