INDEX

Explanations

a variety of common words and phrases, especially contractions ending in 's or 'll, or progressive verbs like 'going'

oai_token-act-pair · gemini-2.0-flash

s

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

<bos>

-1.23

’

-0.55

}")

-0.49

 محفوظة

-0.49

Hozzáférés

-0.48

ритори

-0.47

клопе

-0.47

cong

-0.47

mite

-0.44

POSITIVE LOGITS

 المعيارى

0.75

 snippetHide

0.68

ällor

0.66

dairy

0.61

 Réponses

0.60

anskje

0.59

 виправивши

0.59

 Henley

0.58

 Nema

0.57

 contextLoads

0.57

Activations Density 1.533%

a variety of common words and phrases, especially contractions ending in 's or 'll, or progressive verbs like 'going'

s

No Comments

No Known Activations