© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1121
    Prev
    Next
    INDEX
    Explanations

    various "be" verbs and related words that indicate speculation or certainty about a future event

    oai_token-act-pair · gemini-2.0-flash

    negative sentiment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     '/',
    -0.52
    ]._
    -0.52
     "\""
    -0.50
     Neurology
    -0.48
     confort
    -0.48
     invers
    -0.47
    ("/");
    -0.47
    ('/');
    -0.46
    BaseAdapter
    -0.46
    ocellular
    -0.44
    POSITIVE LOGITS
    Personensuche
    0.74
    Portale
    0.70
    تقاوى
    0.66
    ConstraintMaker
    0.66
    zzleHttp
    0.58
     snippetHide
    0.57
     nahilalakip
    0.57
    AddTagHelper
    0.57
    izoen
    0.56
    DeleteBehavior
    0.55
    Activations Density 2.136%

    No Known Activations