INDEX

Explanations

forms of the verb "to be" along with adjectives

oai_token-act-pair · gemini-2.0-flash

to be

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

DockStyle

-1.01

 disambiguazione

-0.99

 Vikipedi

-0.76

webElementXpaths

-0.73

 Мексичка

-0.71

endphp

-0.70

tanleria

-0.69

 otomatig

-0.69

Rhestr

-0.66

 bezeichneter

-0.65

POSITIVE LOGITS

<bos>

0.85

the

0.65

 their

0.50

 today

0.50

الص

0.42

 everything

0.42

 tonight

0.41

The

0.41

his

0.40

 your

0.40

Activations Density 3.274%

forms of the verb "to be" along with adjectives

to be

No Comments

No Known Activations