© 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. 13447
    Prev
    Next
    INDEX
    Explanations

    sentences with "Ich" (I) or "Brief" (letter), "Zeit" (time), and words related to grammar and language

    oai_token-act-pair · gemini-2.0-flash

    German and code

    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
    Cordialement
    -0.40
     cuer
    -0.40
    kö
    -0.39
     Let
    -0.39
    とも
    -0.38
    //*[@
    -0.38
    っと
    -0.36
    Let
    -0.36
    gnum
    -0.35
    _{\
    -0.34
    POSITIVE LOGITS
    RTDA
    0.94
    MessageTagHelper
    0.84
    AndEndTag
    0.82
    +#+
    0.79
    DockStyle
    0.76
     itſelf
    0.76
    sizeCache
    0.71
     الرياضيه
    0.71
     GenerationType
    0.70
     préféré
    0.69
    Activations Density 0.862%

    No Known Activations