© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4553
    Prev
    Next
    INDEX
    Explanations

    a hodgepodge of fragments of sentences with little thematic coherence.

    oai_token-act-pair · gemini-2.0-flash

    terms related to darkness or dim conditions

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

    darkness

    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
    ⓧ
    -0.61
    CURS
    -0.57
    Palindrome
    -0.57
    UserScript
    -0.55
    štění
    -0.54
    ftance
    -0.54
    ười
    -0.54
    таратура
    -0.53
    *<
    -0.51
     jadx
    -0.50
    POSITIVE LOGITS
     dark
    1.24
    dark
    1.05
     DARK
    1.04
    Dark
    1.03
     Dark
    1.02
    DARK
    0.92
     darken
    0.90
     darkness
    0.86
     mør
    0.80
     dimly
    0.79
    Activations Density 1.368%

    No Known Activations