INDEX

Explanations

the word "more" or comparative adjectives

oai_token-act-pair · gemini-2.0-flash

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 springfox

-0.66

 Walkover

-0.64

chapper

-0.63

 ModelExpression

-0.63

 Emits

-0.60

قایناق‌لار

-0.59

:✨

-0.57

djangoproject

-0.56

 newBuilder

-0.56

abestanden

-0.55

POSITIVE LOGITS

WhereInput

0.55

 unan

0.54

 <=",

0.53

 merkezi

0.52

Distribuzione

0.51

ousness

0.51

canActivate

0.51

둥

0.50

 EClass

0.50

uncur

0.50

Activations Density 1.408%

the word "more" or comparative adjectives

more

No Comments

No Known Activations