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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 193
    Prev
    Next
    INDEX
    Explanations

    phrases that state that something is a solution and phrases including the word available.

    oai_token-act-pair · gemini-2.0-flash

    Technical or code descriptions

    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
    IUrlHelper
    -0.67
    באנגלית
    -0.52
    providedIn
    -0.50
    ="@+
    -0.49
    AndEndTag
    -0.49
    awtextra
    -0.47
    bewerken
    -0.46
    LEGGI
    -0.45
    دانشنامهٔ
    -0.44
    webElementXpaths
    -0.44
    POSITIVE LOGITS
     AssemblyTitle
    0.60
     ejus
    0.59
     ſmall
    0.58
    lilik
    0.56
    TAT
    0.56
     purpoſe
    0.56
    ثيق
    0.56
    ydd
    0.56
    JvmStatic
    0.55
    Conclusions
    0.55
    Activations Density 1.938%

    No Known Activations