INDEX

Explanations

numerical digits, especially those beginning with "2"

oai_token-act-pair · gemini-2.0-flash

2

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>

-2.97

 виправивши

-1.29

 Савезне

-1.25

 Мексичка

-1.16

хьтан

-1.12

Билгалдахарш

-1.10

 gynhyrchwyd

-1.05

 صوتيه

-1.03

 Paglinawan

-1.02

 disambiguazione

-1.00

POSITIVE LOGITS

0.61

0.60

an

0.54

↵

0.49

0.48

0.46

0.45

шка

0.45

–

0.44

Activations Density 0.284%

numerical digits, especially those beginning with "2"

2

No Comments

No Known Activations