© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2372
    Prev
    Next
    INDEX
    Explanations

    phrases that express sentiment

    oai_token-act-pair · gemini-2.0-flash

    admiration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    numerusform
    -0.42
    metis
    -0.42
    nam
    -0.42
    arana
    -0.42
    divide
    -0.40
    uş
    -0.40
     Ces
    -0.40
    medies
    -0.39
    ุง
    -0.38
    ain
    -0.38
    POSITIVE LOGITS
    VIAF
    0.73
    
    0.70
    xFFFFFFFF
    0.68
    xffffffff
    0.66
    ########.
    0.66
    <?
    0.63
    ritsar
    0.63
     commend
    0.63
     оригіналу
    0.62
    })`
    0.61
    Activations Density 1.699%

    No Known Activations