© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10808
    Prev
    Next
    INDEX
    Explanations

    the end of sentences or descriptions, particularly when talking about features

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -0.43
    常
    -0.40
    utnik
    -0.39
    oro
    -0.39
     AppComponent
    -0.39
     consultato
    -0.38
     常
    -0.37
    ть
    -0.37
    ne
    -0.37
    V
    -0.37
    POSITIVE LOGITS
     leaſt
    0.69
     Theſe
    0.68
     raiſ
    0.66
     itſelf
    0.63
     houſe
    0.63
     themſelves
    0.63
    hematical
    0.60
     whoſe
    0.60
     Efq
    0.59
     myſelf
    0.59
    Activations Density 0.199%

    No Known Activations