© 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. 2809
    Prev
    Next
    INDEX
    Explanations

    words and phrases commonly used when describing the height of something or someone as well as in computer code

    oai_token-act-pair · gemini-2.0-flash

    code and measurement descriptions

    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
     length
    -1.73
     Length
    -1.60
     size
    -1.59
     thickness
    -1.59
     lengths
    -1.58
    Length
    -1.57
     height
    -1.53
     thicknesses
    -1.48
    length
    -1.48
     width
    -1.46
    POSITIVE LOGITS
    }}}{\
    0.45
    ashing
    0.42
    pyplot
    0.40
    ----</
    0.38
    ')));
    0.37
    }>;
    0.35
    ()]);
    0.35
     }}>
    0.34
    ']);
    0.34
    ))))))))
    0.34
    Activations Density 2.179%

    No Known Activations