INDEX

Explanations

content-free words and parts of speech such as articles, prepositions, conjunctions, pronouns, auxiliary verbs, and some adjectives.

oai_token-act-pair · gemini-2.0-flash

the

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 câte

-0.62

 înal

-0.53

 ziua

-0.49

 înc

-0.48

 cauza

-0.48

 comigo

-0.47

CppMethod

-0.47

 picioare

-0.47

 løpet

-0.46

íncia

-0.46

POSITIVE LOGITS

RegressionTest

0.60

ImageField

0.60

RenderAtEndOf

0.59

 الدولى

0.59

LookAnd

0.56

 propOrder

0.56

GroupLayout

0.56

 screen

0.56

 PopupWindow

0.55

graphiques

0.55

Activations Density 2.432%

content-free words and parts of speech such as articles, prepositions, conjunctions, pronouns, auxiliary verbs, and some adjectives.

the

No Comments

No Known Activations