© 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. 6320
    Prev
    Next
    INDEX
    Explanations

    a mix of words related to strong emotions, possibly in a fantasy context

    oai_token-act-pair · gemini-2.0-flash

    multilingual words and phrases

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

    Emotions

    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
    SerializedName
    -0.62
     Roskov
    -0.54
    endphp
    -0.52
    "';
    -0.52
    EndGlobalSection
    -0.51
    nocache
    -0.51
    \"");
    -0.49
    *);
    -0.48
    ()];
    -0.48
    InputTagHelper
    -0.48
    POSITIVE LOGITS
     محفوظة
    0.82
    AndEndTag
    0.66
     peindre
    0.63
    出版年
    0.62
     оригіналу
    0.62
     croire
    0.62
     Grecs
    0.62
     vérit
    0.60
    قایناق‌لار
    0.60
    脚注の使い方
    0.59
    Activations Density 2.062%

    No Known Activations