© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10570
    Prev
    Next
    INDEX
    Explanations

    text in Japanese or Russian, as well as math symbols and words related to bones and transplantation

    oai_token-act-pair · gemini-2.0-flash

    ご. All other methods failed to produce a reasonable explanation

    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
    NUMX
    -0.98
     itſelf
    -0.93
     ་་
    -0.87
     ―――――
    -0.85
    ^(@)
    -0.82
     photolibrary
    -0.82
     XNUMX
    -0.82
     TPE
    -0.80
    ſelves
    -0.78
     referrerpolicy
    -0.78
    POSITIVE LOGITS
    もちゃ
    0.43
    客様
    0.40
    世話
    0.36
    詫
    0.36
    つまみ
    0.34
    しゃれ
    0.33
    気に入りの
    0.33
     out
    0.33
     ini
    0.31
     sti
    0.31
    Activations Density 0.056%

    No Known Activations