© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12077
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming-related content, particularly SQL queries, conditions, expressions, and function declarations.

    oai_token-act-pair · gemini-2.0-flash

    conditional expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     pleaſure
    -0.76
     Reſ
    -0.70
     Monfieur
    -0.69
     Anſ
    -0.68
     Eſ
    -0.67
    ///</
    -0.66
     ſtate
    -0.65
     juſ
    -0.65
     Houſe
    -0.65
     ſte
    -0.65
    POSITIVE LOGITS
    writeFieldEnd
    0.56
    tagext
    0.51
    WhereInput
    0.51
    +#+#
    0.49
     ModelExpression
    0.49
    COND
    0.47
    WriteAttribute
    0.46
    <eos>
    0.44
    block
    0.44
     Roskov
    0.43
    Activations Density 2.312%

    No Known Activations