INDEX

Explanations

single character variable names and related code terms

oai_token-act-pair · gemini-2.0-flash

code

np_max-act · 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

Negative Logits

queryInterface

-0.57

du

-0.52

충

-0.50

tra

-0.49

{{\

-0.49

ρους

-0.49

pro

-0.49

Cap

-0.48

><!--

-0.47

ni

-0.47

POSITIVE LOGITS

+#+#

0.74

Rhestr

0.68

RectangleBorder

0.65

setVerticalGroup

0.63

expandindo

0.62

tagext

0.62

IntoConstraints

0.60

 للمعارف

0.59

 ExecuteAsync

0.57

 ModelExpression

0.56

Activations Density 14.173%

single character variable names and related code terms

code

No Known Activations