© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 457
    Prev
    Next
    INDEX
    Explanations

    the number "ten", the words "each," "one" and measurements of some kind.

    oai_token-act-pair · gemini-2.0-flash

    one

    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
    WebVitals
    -0.86
    GEBURTSDATUM
    -0.83
    ########.
    -0.79
     مشين
    -0.77
     StatefulWidget
    -0.76
    +#+#
    -0.72
    GraphicsUnit
    -0.72
     snippetHide
    -0.72
    sizeCache
    -0.71
    بوابة
    -0.70
    POSITIVE LOGITS
     go
    0.41
     pass
    0.39
    complexType
    0.38
     zkou
    0.37
    ografija
    0.35
     doua
    0.34
    omock
    0.33
    Aceptar
    0.32
     Le
    0.31
     Up
    0.31
    Activations Density 1.885%

    No Known Activations