INDEX

Explanations

words and phrases related to enjoying and recommending books and food

oai_token-act-pair · gemini-2.0-flash

positive adjectives

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

<bos>

-0.68

WireFormatLite

-0.65

SpringRunner

-0.61

AZINE

-0.59

KommentareTeilen

-0.59

 defStyleAttr

-0.56

')))

-0.56

بوت

-0.54

Ausstattung

-0.54

èses

-0.54

POSITIVE LOGITS

GEBURTSDATUM

0.54

WebElementEntity

0.54

 незавершена

0.52

Smarty

0.50

addCriterion

0.48

 Samaria

0.46

 useAuth

0.43

 INTERESAR

0.42

WriteLiteral

0.42

InSection

0.41

Activations Density 2.385%

words and phrases related to enjoying and recommending books and food

positive adjectives

No Comments

No Known Activations