© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13644
    Prev
    Next
    INDEX
    Explanations

    the prefix "Cro" appearing in words related to crocodiles or people's names

    oai_token-act-pair · gemini-2.0-flash

    Cro

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     betweenstory
    -0.72
    ніципа
    -0.71
    ьаж
    -0.71
    ########.
    -0.63
     חיצוניים
    -0.63
    matchCondition
    -0.63
    ViewFeatures
    -0.62
     <=",
    -0.58
    sizeCache
    -0.57
    lecular
    -0.57
    POSITIVE LOGITS
    }],
    0.67
    rizona
    0.57
    Bonne
    0.47
    mybatisplus
    0.46
    "])){
    0.45
     */;
    0.45
    }]
    0.44
    )";
    0.44
    '])){
    0.40
    PPT
    0.40
    Activations Density 0.181%

    No Known Activations