© 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. 8899
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to research and professional industries (news, finance, tech, medicine, law, etc.).

    oai_token-act-pair · gemini-2.0-flash

    Technical concepts and improvements

    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
    τως
    -0.54
    SWIG
    -0.47
    >{@
    -0.46
    haja
    -0.46
    TRAILING
    -0.45
    UnknownFields
    -0.45
    GINS
    -0.44
    propTypes
    -0.43
    MutableLiveData
    -0.42
     touche
    -0.42
    POSITIVE LOGITS
    CppMethod
    0.74
    migrationBuilder
    0.70
    ValueStyle
    0.69
    httphttps
    0.65
    KommentareTeilen
    0.63
     Monro
    0.60
    labelledby
    0.59
    principalColumn
    0.58
     Bili
    0.54
    encils
    0.54
    Activations Density 14.886%

    No Known Activations