© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6365
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly in languages like Java, Javascript, or C++

    oai_token-act-pair · gemini-2.0-flash

    technical terms and programming keywords

    np_token-act-pair-logits · gpt-4o-mini

    Non-English/code words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     a
    -0.59
    ,
    -0.49
    t
    -0.45
    िन्न
    -0.45
    .
    -0.44
    <unused63>
    -0.44
     grun
    -0.44
     aprovechar
    -0.43
    <unused61>
    -0.43
     de
    -0.42
    POSITIVE LOGITS
     فريبيس
    1.07
     smtplib
    1.05
     Roskov
    1.00
     Bioaccumulative
    0.94
    RegressionTest
    0.93
    Autoritní
    0.92
    +#+#
    0.87
     ModelExpression
    0.86
     متعلقه
    0.86
     protoimpl
    0.85
    Activations Density 18.966%

    No Known Activations