INDEX

Explanations

code snippets, acronyms and URLs

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 pulso

-0.49

恭喜

-0.45

erover

-0.44

lave

-0.43

 να

-0.43

zensionen

-0.43

 alphabetically

-0.42

("")]

-0.41

invokeLater

-0.41

TableBody

-0.41

POSITIVE LOGITS

ValueStyle

0.94

GEBURTSDATUM

0.88

AccessorTable

0.86

<bos>

0.85

RegressionTest

0.81

sizeCache

0.81

 '\\;'

0.77

 مشين

0.77

וויק

0.74

 estimés

0.73

Activations Density 1.153%

code snippets, acronyms and URLs

No Comments

No Known Activations