INDEX

Explanations

code snippets and command-line arguments with dashes, compiler flags and conditional statements.

oai_token-act-pair · gemini-2.0-flash

hyphens

np_max-act · gemini-2.0-flash

New Auto-Interp

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 resourceCulture

-0.81

SharedDtor

-0.64

LayoutStyle

-0.56

 виправивши

-0.56

ysacchar

-0.56

MarshalTo

-0.56

 EClass

-0.55

complexContent

-0.54

avadoc

-0.54

vician

-0.53

POSITIVE LOGITS

 feature

0.57

 specification

0.53

 settings

0.49

ágos

0.48

FEATURES

0.48

topt

0.48

 Fland

0.47

Ắ

0.47

feature

0.47

 sett

0.47

Activations Density 1.938%

code snippets and command-line arguments with dashes, compiler flags and conditional statements.

hyphens

No Comments

No Known Activations