© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11337
    Prev
    Next
    INDEX
    Explanations

    words and phrases suggesting advantages, improvements, or positive outcomes

    oai_token-act-pair · gemini-2.0-flash

    terms related to benefits and advantages

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

    benefit

    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
    évaluateur
    -0.57
    ništ
    -0.57
    complexContent
    -0.56
     onOptions
    -0.56
    ंदीखरीदारी
    -0.56
    WebServlet
    -0.56
    Nguồn
    -0.56
    potranspiration
    -0.55
     tartalomajánló
    -0.55
     Winaray
    -0.55
    POSITIVE LOGITS
     ffilm
    0.54
    CopyWith
    0.51
    CWE
    0.46
     виправивши
    0.44
    made
    0.44
    nec
    0.44
    Tune
    0.44
    +#+#
    0.41
    исленность
    0.40
    Made
    0.40
    Activations Density 10.301%

    No Known Activations