© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16048
    Prev
    Next
    INDEX
    Explanations

    XML and HTML headers

    oai_token-act-pair · gemini-2.0-flash

    web addresses 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
    #,
    -0.59
     الاطلاع
    -0.56
     surla
    -0.55
     www
    -0.54
     "");
    -0.54
    はじめに
    -0.53
     *@
    -0.52
    Hauptartikel
    -0.52
    }-*/;
    -0.52
     Having
    -0.52
    POSITIVE LOGITS
    LookAnd
    0.51
    CppMethod
    0.50
    NUMX
    0.50
    følgelig
    0.49
     literals
    0.44
    XMLSchema
    0.44
     tongues
    0.44
    InvalidProtocol
    0.44
     XCTest
    0.43
    ANDUM
    0.43
    Activations Density 0.762%

    No Known Activations