© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2057
    Prev
    Next
    INDEX
    Explanations

    mentions of searching, discovering, or trying to find things

    oai_token-act-pair · gemini-2.0-flash

    searching

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    istoitu
    -0.51
    ])));
    -0.51
     protoimpl
    -0.50
     дописавши
    -0.48
     conoció
    -0.48
    finding
    -0.46
    "]));
    -0.46
    ])),
    -0.44
    Find
    -0.44
    });
    -0.44
    POSITIVE LOGITS
     out
    0.86
    partimento
    0.57
     electors
    0.56
     common
    0.55
    تفصیلات
    0.54
     signatures
    0.54
     незавершена
    0.54
    out
    0.54
     there
    0.53
     three
    0.53
    Activations Density 13.302%

    No Known Activations