© 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. 3097
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs like "is," "'s," "was," and helping verbs like "should".

    oai_token-act-pair · gemini-2.0-flash

    technical terms and programming-related words

    np_token-act-pair-logits · gpt-4o-mini
    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
     Isu
    -0.54
    lankton
    -0.52
     perfor
    -0.49
    φαλ
    -0.48
    pexpr
    -0.48
    Condu
    -0.48
     forState
    -0.48
    pyrid
    -0.48
    zzarella
    -0.47
     mirage
    -0.47
    POSITIVE LOGITS
    sendFile
    0.55
     HttpServlet
    0.53
    RTCF
    0.51
     côtes
    0.51
     comerciais
    0.51
    HttpFoundation
    0.51
    Geplaatst
    0.51
    __":
    0.49
     nakalista
    0.49
     familiari
    0.49
    Activations Density 1.221%

    No Known Activations