© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7154
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to internet marketing, cookies and online dating services

    oai_token-act-pair · gemini-2.0-flash

    internet activity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Erreferentziak
    -0.63
     transfieras
    -0.57
    Hentet
    -0.55
    fromnode
    -0.55
    XtraReports
    -0.53
    kent
    -0.52
    egli
    -0.51
    jiga
    -0.50
    Referencies
    -0.50
    jupiter
    -0.49
    POSITIVE LOGITS
    ]='\
    0.71
    ]--;
    0.63
    ]};
    0.61
    ])).
    0.52
    ]++;
    0.51
    */].
    0.50
    Vidu
    0.50
    JoinColumn
    0.49
    ={`/
    0.49
    //
    0.48
    Activations Density 0.986%

    No Known Activations