INDEX

Explanations

seemingly random numbers or section markers such as "Sec" that are likely associated with research papers

oai_token-act-pair · gemini-2.0-flash

digits

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

subsection

-0.87

subsubsection

-0.86

nextProps

-0.54

Ob

-0.51

ob

-0.49

meno

-0.48

-0.47

ital

-0.47

balleur

-0.47

pes

-0.47

POSITIVE LOGITS

 transférez

0.79

 ujednoznacz

0.71

 betweenstory

0.69

IndentedString

0.68

 kasarigan

0.68

 initComponents

0.62

expandindo

0.61

 للاسماء

0.61

 فريبيس

0.61

AutoScale

0.61

Activations Density 0.844%

seemingly random numbers or section markers such as "Sec" that are likely associated with research papers

digits

No Comments

No Known Activations