© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 4398
    Prev
    Next
    INDEX
    Explanations

    words relating to animal testing and scientific experiments on animals

    oai_token-act-pair · gemini-2.0-flash

    Animal experiments

    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
    MLLoader
    -0.65
     '\\;'
    -0.57
    GeneratedValue
    -0.52
     محفوظة
    -0.52
     Entdecken
    -0.49
    oa̍t
    -0.47
    pektive
    -0.47
    uste
    -0.46
    meyen
    -0.46
    త్
    -0.45
    POSITIVE LOGITS
    ]")]
    0.69
    NSIndexPath
    0.69
    :+:
    0.66
    
    0.61
    enumii
    0.59
     ThemeData
    0.57
    principalColumn
    0.56
     الحره
    0.52
    +#+#
    0.51
     InputDecoration
    0.51
    Activations Density 4.188%

    No Known Activations