© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7494
    Prev
    Next
    INDEX
    Explanations

    complex sentences with a lot of punctuation that expresses opinions or feelings

    oai_token-act-pair · gemini-2.0-flash

    the word 'especially' in various forms

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

    comma

    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
     SEDS
    -0.63
     EconPapers
    -0.60
    ⓧ
    -0.57
    AutoScaleMode
    -0.55
    かれています
    -0.54
    principalColumn
    -0.54
    boh
    -0.54
    )))),
    -0.53
     муніципалі
    -0.53
    rolla
    -0.52
    POSITIVE LOGITS
     especially
    2.84
    Especially
    2.77
     Especially
    2.67
    especially
    2.59
     particularly
    2.41
     Particularly
    2.27
     especialmente
    2.23
    particularly
    2.22
     ESPEC
    2.05
     особенно
    1.98
    Activations Density 4.285%

    No Known Activations