© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15661
    Prev
    Next
    INDEX
    Explanations

    mathematical and chemical notation

    oai_token-act-pair · gemini-2.0-flash

    Math and science text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    }
    -1.05
     }
    -1.05
    ]
    -0.95
    )
    -0.89
    ()
    -0.70
     )
    -0.69
    >
    -0.64
     ]
    -0.60
     \}
    -0.58
     ")
    -0.54
    POSITIVE LOGITS
     autorytatywna
    0.65
    ::_('
    0.65
    הערות
    0.64
     MainAxisSize
    0.63
    :'/
    0.61
    󠁴
    0.60
    ंदीखरीदारी
    0.60
     مشين
    0.58
     الحره
    0.58
    Personensuche
    0.57
    Activations Density 1.618%

    No Known Activations