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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3496
    Prev
    Next
    INDEX
    Explanations

    Swedish words and names, especially those containing the letters "ls".

    oai_token-act-pair · gemini-2.0-flash

    Swedish 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_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
     der
    -0.40
     at
    -0.40
     for
    -0.40
     ao
    -0.39
     y
    -0.39
     og
    -0.39
     ((
    -0.38
    лом
    -0.38
     um
    -0.38
     ve
    -0.38
    POSITIVE LOGITS
     varandra
    1.04
     skolen
    1.00
     stället
    0.97
     skolan
    0.94
     vägen
    0.91
     enfans
    0.91
     Monfieur
    0.91
     bakgrund
    0.91
     besök
    0.91
     myſelf
    0.90
    Activations Density 2.473%

    No Known Activations